作者中心
专家审稿
责编办公
编辑办公
-
摘要: 特定辐射源个体识别依赖设备发射信号的“射频指纹”微弱差异识别辐射源所属个体身份属性，是支撑无线安全、频谱管控和态势感知的重要基石。随着无线场景的多样化与动态化，单一域(源域与目标域分布相同)下训练的深度学习模型往往在跨接收机、跨时间等真实环境中性能急剧下降，目前缺乏关于该方面全面、细致的综述。基于此，该文首先对跨场景类型进行分类，然后系统归纳总结主流算法框架及代表性方法，着重剖析每类方法的核心思想与关键技术，并总结了主要开源跨场景数据集，最后指出当前研究的瓶颈与未来可能方向，旨在推动复杂电磁环境下的辐射源个体识别理论和方法研究的新发展。
-
关键词:
- 跨场景特定辐射源识别 /
- 射频指纹 /
- 深度学习 /
- 迁移学习 /
- 域适应
Abstract: Specific emitter identification (SEI) relies on subtle differences in the radio-frequency fingerprints of device-emitted signals to determine the emitter identity attributes. SEI plays a fundamental role in wireless security, spectrum management, and situational awareness. However, as wireless scenarios become increasingly diverse and dynamic, deep learning models trained in a single domain (where the source and target domains share the same distribution) often suffer severe performance degradation in real-world settings such as cross-receiver and cross-time scenarios. This degradation has not yet been comprehensively analyzed. To address this issue, this paper first classifies SEI according to cross-scenario types, and then systematically reviews mainstream algorithm frameworks and representative SEI methods, with a particular focus on the core ideas and key technologies underlying each method. It also summarizes the main open-source cross-scenario SEI datasets. Finally, the paper identifies current research bottlenecks and outlines potential future directions, aiming to facilitate advances in SEI theories and methodologies applicable to complex electromagnetic environments. -
表 1 基于对抗式域对齐的跨单源域识别算法对比[26−35]
Table 1. Comparison of cross-single-domain identification algorithms based on adversarial domain alignment[26−35]
算法 核心工作 算法不足 跨场景类型 效果分析 ACR-SEI 结合对抗训练与一致性正则化
提升跨域特征稳定性依赖高质量未标注数据，对抗训练稳定性待提升 跨接收机、
空间场景在ORACLE射频指纹数据集中准确率最高99%(12 dB环境)[26] DADA 采用对抗生成网络对齐源域与
目标域特征分布对目标域数据分布差异敏感，对抗训练耗时长 跨空间场景 在自建数据集中准确率最高99.28%(25 dB环境)[27] UAV-DANN 结合Transformer和DANN联合
对齐信号分布不适应低信噪比场景，泛化能力受限 跨空间场景 在自建无人机遥控数据集上准确率最高88.35%[28] SSDA-AMR 联合半监督学习与域不变特征提取，解决调制类型变化问题 需部分目标域标注，复杂调制场景性能下降 跨调制场景 在RadioML2016.10A、RadioML2018.01A和自定义数据集上准确率可超过90%(0dB环境)[29] OpenRF 基于真实5G平台实现端到端指纹认证 依赖特定硬件环境，泛化能力受限 跨空间、
协议场景在POWDER平台自建数据集上准确率99.86%[30] FRFDA 联邦框架下实现多源模型参数迁移，保护隐私 通信开销大，异构设备
兼容性差跨空间场景 在POWDER平台自建数据集上准确率90.33%(4G、5G、Wi-Fi混合数据)[31] DA-VMSEI 自适应调制参数估计与域对齐
联合优化对调制参数突变适应性不足 跨调制场景 在自建数据集上准确率85%
(4 dB环境)[32]DADF 利用深度神经网络从原始信号中提取鲁棒且可区分的设备指纹特征 在极端或未见过的领域条件下，泛化能力会下降 跨空间、
功率场景在自建数据集上准确率最高99.7%[33] DDA-DN 引入动态噪声补偿模块，结合对抗性域适应实现变环境下的稳定识别 对噪声统计特性突变敏感，
需预先建模噪声分布跨空间场景 在自建数据集上准确率82%[34]
(6 dB环境)CBAM-CNN-BDA 融合通道注意力机制与双向域对抗网络，增强指纹的细粒度特征表达与
跨接收机适配能力注意力模块对接收机硬件参数敏感，需接收机端先验校准 跨接收机场景 在自建数据集上准确率97.5%[35] 
下载: 导出CSV
表 2 基于分布度量对齐的跨单源域识别算法对比[36−41]
Table 2. Comparison of cross-single-domain identification algorithms based on distribution metric alignment[36−41]
算法 核心工作 算法不足 跨场景类型 效果分析 AMC-SS 联合对抗训练与多约束优化解决未标注样本特征漂移问题 对抗约束设计复杂，计算成本高 跨接收机场景 在自建数据集上准确率99%[36] DAN 提出通过多层MK-MMD对齐特征分布 对源域数据量依赖性强，
计算复杂度较高跨时间场景 使用公开数据集(Office-31、Office-Caltech、ImageCLEF-DA)最高平均准确率84.6%[37] JSA 构建跨接收机的联合子空间实现辐射源特征不变性表征 子空间维度敏感，
动态环境适应性弱跨接收机场景 在自建数据集上准确率超过85%[38] MSTL 基于子域粒度聚合多源知识，提升跨域泛化能力 子域划分依赖先验知识，异构源域兼容性差 跨频域场景 在自建数据集上准确率88%[39] DSBN 分离领域特有统计量，实现无监督域适应中特征分布解耦 需足够目标域批量样本，
域间差异过大时失效跨接收机场景 使用VisDA-C(平均80.2%)、Office-31(平均88.3%)、Office-Home数据集(平均83.0%)[40] MDAN 构建多级域差异度量模块，采用层次化特征对齐 计算复杂度高，
多差异权重需手动调整跨接收机、时间场景 在ORACLE数据集上识别率93.1%[41]
下载: 导出CSV
Table 3. Comparison of cross-single-domain identification algorithms based on contrastive learning[42−46]
算法 核心工作 算法不足 跨场景类型 效果分析 CSSL-PL 结合对比学习与伪标签机制，增强在低标注率下的判别性特征学习 伪标签噪声抑制能力有限，
复杂调制场景鲁棒性下降跨调制、空间场景 在自建数据集上准确率超过85%(SNR大于-2dB环境)[42] SSDF 基于自监督的双流特征编码器融合时频域信息，缓解小样本的
过拟合问题双流模型计算开销大，动态场景特征同步性要求高 跨接收机、空间场景 在自建数据集上准确率97.1%[43] CDA-PTN 结合原型网络和小样本学习，
能在无标注时实现高效的识别对域间分布差异过大的场景泛化能力有限 跨空间、接收机、
功率场景使用ORACLE、CORES、WiSig数据集，最高准确率99%[44] UCL-TS 引入时域偏移不变性约束的无监督对比学习框架 依赖高质量无标签时序数据，短时突变适应性不足 跨时间场景 在自建数据集上准确率88.2%(无线信道环境，时间跨1天)[45] TPML 结合了伪标签和元学习机制，
可适应动态电磁场景依赖源域质量，伪标签的准确性可能显著下降 跨时间场景 在自建数据集上准确率90%[46]
下载: 导出CSV
表 4 基于多源对抗式域对齐的跨多源域识别算法对比[47−49]
Table 4. Comparison of cross-multiple-domain identification algorithms based on multi-source adversarial domain alignment[47−49]
算法 核心工作 算法不足 跨场景类型 效果分析 PBDA 提出原型中心双对齐机制
(特征空间+原型分布对齐)对噪声和杂波敏感，
需高纯度原型初始化跨空间、
接收机场景使用ImageCLEF-DA(平均90.2%)、Office-31
(平均91.4%)、Office-Home(平均75.5%)
和自建数据集(超过88%)[47]ADAW 提出基于Wasserstein距离的
对抗域适应框架依赖大规模跨会话数据集，
计算复杂度高跨时间场景 ADS-B自建数据集中准确率最高86.78%[48] MFGADA 融合多分类器差异损失与梯度对齐策略，
提升了跨批次数据的特征对齐效果测试时间跨度小，
不适应实际场景跨时间场景 在自建数据集上平均准确率79.49%[49]
下载: 导出CSV
表 5 基于分布度量对齐的跨多源域识别算法对比[50−52]
Table 5. Comparison of cross-multiple-domain identification algorithms based on distribution metric alignment[50−52]
下载: 导出CSV
Table 6. Comparison of cross-multiple-domain identification algorithms based on contrastive learning[53−54]
下载: 导出CSV
Table 7. Comparison of cross-multiple-domain identification algorithms based on relationship modeling[55−56]
下载: 导出CSV
算法 核心工作 算法不足 跨场景类型 效果分析 CRDL-RF 利用多数据流融合增强信道鲁棒性，解决动态信道干扰下的设备指纹识别问题 计算复杂度高，依赖多模态数据同步采集 跨空间、协议场景 在自建数据集上准确率92%
(0 dB环境，相同瑞利信道
进行训练和测试)[57]AirID 通过注入定制化指纹提升无人机身份认证的独特性与抗伪造能力 需硬件生成特定畸变，
适配场景受限跨接收机、空间场景 在自建数据集上准确率98%[58] DeepFIR 自适应波形滤波抑制信道噪声，结合深度网络实现高鲁棒的物理层信号分类 实时性较差，滤波器参数
动态调整依赖离线训练跨空间、时间场景 在自建数据集上准确率74%
(10个滤波器头条件下)[59]RTAWS 实时生成抗干扰波形优化神经网络分类鲁棒性，支持动态信道反馈机制 依赖反馈链路延迟，
多用户场景资源竞争跨频域场景 使用DeepSig RADIOML 2018.01A和Wi-Fi信号自建数据集，在BPSK、16QAM、64QAM上识别准确率较对照组提升1.24倍、4.1倍、2.9倍[60] DACR-RFF 多模态数据增强以扩展RFF的
跨信道泛化能力存储与预处理成本高，增强数据可能引入分布偏移 跨接收机、空间、
时间场景使用美国DARPA提供的Wi-Fi数据集上准确率80%[61] LVNR-RFF 动态特征对齐模块支持可变长信号输入，抗噪声特征提取提升低信
噪比场景性能模型复杂度高，长序列推理延迟显著 跨空间场景 在自建数据集上，识别准确率67.26%(10 dB环境)[62]
下载: 导出CSV
表 9 开源跨场景辐射源个体识别数据集[30,75,77−89]
Table 9. Open-source cross-scenario emitter individual identification datasets[30,75,77−89]
数据集 发射端 接收端 信号类型 跨场景方式 ORACLE[77] USRP X310 USRP B210 IEEE802.11a 跨空间场景 ShawabkaINFOCOM2020[75] USRP N210/X310 USRP N210 IEEE802.11a/g 跨时间、接收机场景 WiSig[78] WiFi USRP B210/N210/X310 IEEE802.11a/g 跨时间、接收机场景 RFFP-dataset[79] Pycom IoT USRP B210 LoRa、WiFi 跨时间、空间、接收机、通信协议场景 POWDER[30] USRP X310 USRP B210 5G、WiFi、LTE 跨时间、空间、接收机场景 RadarCommDataset[80] 多种仿真或实际雷达、通信设备 USRP N210 雷达、通信信号 跨空间、调制方式场景 AirID[81] SDR UAV SDR UAV/SDR Ground IEEE802.11a 跨时间场景 Hovering UAVs[82] DJI M100 USRP X310 非标准波形 跨空间场景 LoRa-RFFI1[83] LoRa发射机 USRP LoRa 跨空间场景 LoRa-RFFI2[84] LoRa DUTs SDR接收机 LoRa 跨接收机场景 Bluetooth Data[85] Smartphone Tektronix TDS7404 Bluetooth 跨接收机场景 DroneRFa[86] UAVs USRP- 2955 无人机与遥控器通信信号 跨空间、频域场景 DroneRFb-DIR[87] UAVs USRP- 2955 无人机与遥控器通信信号 跨空间、频域场景 MOANA[88] 导航雷达 雷达接收机 导航雷达信号 跨时间、空间、接收机场景 ATCRBS跨模态数据集[89] 地面雷达 飞机应答机 民航雷达信号 跨空间、时间场景
下载: 导出CSV
-
[1] GOK G, ALP Y K and ARIKAN O. A new method for specific emitter identification with results on real radar measurements[J]. IEEE Transactions on Information Forensics and Security, 2020, 15: 3335–3346. doi: 10.1109/TIFS.2020.2988558. [2] WANG Cheng, FU Xue, WANG Yu, et al. Interpolative metric learning for few-shot specific emitter identification[J]. IEEE Transactions on Vehicular Technology, 2023, 72(12): 16851–16855. doi: 10.1109/TVT.2023.3296120. [3] XING Yuexiu, HU Aiqun, ZHANG Junqing, et al. Design of a robust radio-frequency fingerprint identification scheme for multimode LFM radar[J]. IEEE Internet of Things Journal, 2020, 7(10): 10581–10593. doi: 10.1109/JIOT.2020.3003692. [4] XU Zhengwei, HAN Guangjie, LIU Li, et al. A lightweight specific emitter identification model for IIoT devices based on adaptive broad learning[J]. IEEE Transactions on Industrial Informatics, 2023, 19(5): 7066–7075. doi: 10.1109/TII.2022.3206309. [5] LIN Yun, TU Ya, and DOU Zheng. An improved neural network pruning technology for automatic modulation classification in edge devices[J]. IEEE Transactions on Vehicular Technology, 2020, 69(5): 5703–5706. doi: 10.1109/TVT.2020.2983143. [6] 谭凯文, 张立民, 闫文君, 等. 面向非均衡类别的半监督辐射源识别方法[J]. 雷达学报, 2022, 11(4): 713–727. doi: 10.12000/JR22043.TAN Kaiwen, ZHANG Limin, YAN Wenjun, et al. A semi-supervised emitter identification method for imbalanced category[J]. Journal of Radars, 2022, 11(4): 713–727. doi: 10.12000/JR22043. [7] 赵雨睿, 黄知涛, 王翔. 基于相空间重构的辐射源个体识别技术综述[J]. 雷达学报, 2023, 12(4): 713–737. doi: 10.12000/JR23057.ZHAO Yurui, HUANG Zhitao, and WANG Xiang. A review of specific emitter identification based on phase space reconstruction[J]. Journal of Radars, 2023, 12(4): 713–737. doi: 10.12000/JR23057. [8] 张顺生, 丁宦城, 王文钦. 面向辐射源识别的多尺度特征提取与特征选择网络[J]. 国防科技大学学报, 2024, 46(6): 141–148. doi: 10.11887/j.cn.202406015.ZHANG Shunsheng, DING Huancheng, and WANG Wenqin. Multi-scale feature extraction and feature selection network for radiation identification[J]. Journal of National University of Defense Technology, 2024, 46(6): 141–148. doi: 10.11887/j.cn.202406015. [9] 季鹏飞. 单比特超宽带数字信道化接收机关键技术研究[D]. 长沙: 国防科技大学, 2022. doi: 10.27052/d.cnki.gzjgu.2022.000058.JI Pengfei. Research on key technology of monobit UWB digital channelized receiver[D]. Changsha: National University of Defense Technology, 2022. doi: 10.27052/d.cnki.gzjgu.2022.000058. [10] CHEN Qi, YANG Lingxiao, LAI Jianhuang, et al. Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation[C]. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, 2022: 4278–4288. doi: 10.1109/CVPR52688.2022.00425. [11] JIANG Pengtao, YANG Yuqi, HOU Qibin, et al. L2G: A simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation[C]. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, 2022: 16865–16875. doi: 10.1109/CVPR52688.2022.01638. [12] 李昕. 基于无监督学习的通信辐射源个体识别技术研究[D]. 长沙: 国防科技大学, 2019. doi: 10.27052/d.cnki.gzjgu.2019.000718.LI Xin. Research on individual communication transmitter identification based on unsupervised learning[D]. Changsha: National University of Defense Technology, 2019. doi: 10.27052/d.cnki.gzjgu.2019.000718. [13] PERSONS J B, WONG L J, MOORE M O, et al. Classification of radio signals using truncated Gaussian discriminant analysis of convolutional neural network-derived features[C]. MILCOM 2022 - 2022 IEEE Military Communications Conference (MILCOM), Rockville, USA, 2022: 304–310. doi: 10.1109/MILCOM55135.2022.10017724. [14] 王天池, 俞璐. 迁移学习及其在通信辐射源个体识别中的应用[J]. 通信技术, 2022, 55(3): 265–273. doi: 10.3969/j.issn.1002-0802.2022.03.001.WANG Tianchi and YU Lu. Transfer learning and its application in communication emitter identification[J]. Communications Technology, 2022, 55(3): 265–273. doi: 10.3969/j.issn.1002-0802.2022.03.001. [15] TAN Haoyue, ZHANG Zhenxi, LI Yu, et al. Multi-scale feature fusion and distribution similarity network for few-shot automatic modulation classification[J]. IEEE Signal Processing Letters, 2024, 31: 2890–2894. doi: 10.1109/LSP.2024.3470762. [16] 马宾, 王一利, 徐健, 等. 基于双向生成对抗网络的感知哈希图像内容取证算法[J]. 计算机学报, 2023, 46(12): 2551–2572. doi: 10.11897/SP.J.1016.2023.02551.MA Bin, WANG Yili, XU Jian, et al. A bidirectional generative adversarial network-based perceptual hash algorithm for image content forensics[J]. Chinese Journal of Computers, 2023, 46(12): 2551–2572. doi: 10.11897/SP.J.1016.2023.02551. [17] 李奇真, 刘佳旭, 梁先明, 等. 基于深度学习的跨域辐射源个体识别综述[J]. 电讯技术, 2024, 64(7): 1163–1174. doi: 10.20079/j.issn.1001-893x.231030001.LI Qizhen, LIU Jiaxu, LIANG Xianming, et al. Cross-domain specific emitter identification based on deep learning: A comprehensive survey[J]. Telecommunication Engineering, 2024, 64(7): 1163–1174. doi: 10.20079/j.issn.1001-893x.231030001. [18] 张涛涛, 谢钧, 乔平娟. 基于域适应的辐射源个体识别研究综述[J]. 软件导刊, 2024, 23(6): 205–213. doi: 10.11907/rjdk.241261.ZHANG Taotao, XIE Jun, and QIAO Pingjuan. A review of specific emitter identification based on domain adaptation[J]. Software Guide, 2024, 23(6): 205–213. doi: 10.11907/rjdk.241261. [19] YAN Wenjun, LING Qing, YU Keyuan, et al. A pseudolabel method with semantic drift for specific emitter identification[J]. IEEE Transactions on Aerospace and Electronic Systems, 2025, 61(3): 6217–6235. doi: 10.1109/TAES.2025.3527960. [20] 肖望. 面向未知类别的跨域辐射源个体识别方法研究与实现[D]. 电子科技大学, 2025. DOI: 10.27005/d.cnki.gdzku.2025.000389.Xiao Wang. Research and Implementation of Cross-Domain Radiation Source Individual Recognition Method for Unknown Categories [D]. University of Electronic Science and Technology of China, 2025. DOI: 10.27005/d.cnki.gdzku.2025.000389. [21] ZHA Xiong, LI Tianyun, QIU Zhaoyang, et al. Cross-receiver radio frequency fingerprint identification based on contrastive learning and subdomain adaptation[J]. IEEE Signal Processing Letters, 2023, 30: 70–74. doi: 10.1109/LSP.2023.3241592. [22] Y. Zhang, Z. Zhou, Y. Cao, G. Li and X. Li, "Improved Specific Emitter Identification Based on Margin Disparity Discrepancy in Varying Modulation Scenarios," in IEEE Signal Processing Letters, vol. 32, pp. 3375-3379, 2025, doi: 10.1109/LSP.2025.3597100. [23] 杜贵琪. 基于人工智能的射频指纹识别技术研究[D]. 成都: 电子科技大学, 2022. doi: 10.27005/d.cnki.gdzku.2022.004593.DU Guiqi. Radio frequency fingerprint identification technology study based on artificial intelligence[D]. Chengdu: University of Electronic Science and Technology of China, 2022. doi: 10.27005/d.cnki.gdzku.2022.004593. [24] YANG Lu, CAMTEPE S, GAO Yansong, et al. On the use of power amplifier nonlinearity quotient to improve radio frequency fingerprint identification in time-varying channels[C]. 2023 IEEE 34th Annual International Symposium on Personal, Indoor and Mobile Radio Communications, Toronto, Canada, 2023: 1–7. doi: 10.1109/PIMRC56721.2023.10293946. [25] HAMDAOUI B and ELMAGHBUB A. Deep-learning-based device fingerprinting for increased LoRa-IoT security: Sensitivity to network deployment changes[J]. IEEE Network, 2022, 36(3): 204–210. doi: 10.1109/MNET.001.2100553. [26] 王天池, 俞璐, 赫德军. 基于对抗的一致性正则半监督辐射源个体识别方法[J]. 计算机测量与控制, 2023, 31(2): 204–209. doi: 10.16526/j.cnki.11-4762/tp.2023.02.032.WANG Tianchi, YU Lu, and HE Dejun. Individual identification method of adversarial-based consistency regularization semi-supervised emitter[J]. Computer Measurement & Control, 2023, 31(2): 204–209. doi: 10.16526/j.cnki.11-4762/tp.2023.02.032. [27] WANG Jian, ZHANG Bangning, ZHANG Jie, et al. Specific emitter identification based on deep adversarial domain adaptation[C]. 2021 4th International Conference on Information Communication and Signal Processing (ICICSP), Shanghai, China, 2021: 104–109. doi: 10.1109/ICICSP54369.2021.9611854. [28] 查浩然, 刘畅, 王巨震, 等. 面向无人机辐射源个体识别的域适应模型设计[J]. 信号处理, 2024, 40(4): 650–660. doi: 10.16798/j.issn.1003-0530.2024.04.004.ZHA Haoran, LIU Chang, WANG Juzhen, et al. Design of domain-adaptation model for specific emitter identification of UAV signal[J]. Journal of Signal Processing, 2024, 40(4): 650–660. doi: 10.16798/j.issn.1003-0530.2024.04.004. [29] ZHANG Maomao, WEI Guofeng, TANG Peng, et al. Semi-supervised domain adaptation for automatic modulation recognition in unseen scenarios[J]. IEEE Transactions on Cognitive Communications and Networking, 2025, 11(3): 1609–1622. doi: 10.1109/TCCN.2024.3465648. [30] REUS-MUNS G, JAISINGHANI D, SANKHE K, et al. Trust in 5G open RANs through machine learning: RF fingerprinting on the POWDER PAWR platform[C]. 2020 IEEE Global Communications Conference, Taipei, China, 2020: 1–6. doi: 10.1109/GLOBECOM42002.2020.9348261. [31] ZHANG Chuanting, DANG Shuping, ZHANG Junqing, et al. Federated radio frequency fingerprinting with model transfer and adaptation[C]. 2023 IEEE Conference on Computer Communications Workshops, Hoboken, USA, 2023: 1–6. doi: 10.1109/INFOCOMWKSHPS57453.2023.10226112. [32] ZHANG Xinliang, LI Tianyun, GONG Pei, et al. Variable-modulation specific emitter identification with domain adaptation[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 380–395. doi: 10.1109/TIFS.2022.3223794. [33] ELMAGHBUB A and HAMDAOUI B. A needle in a haystack: Distinguishable deep neural network features for domain-agnostic device fingerprinting[C]. 2023 IEEE Conference on Communications and Network Security (CNS), Orlando, USA, 2023, pp. 1–9. doi: 10.1109/CNS59707.2023.10288752. [34] 刘剑锋, 于宏毅, 杜剑平, 等. 基于领域自适应的动态噪声辐射源个体识别[J]. 信号处理, 2021, 37(6): 1000–1007. doi: 10.16798/j.issn.1003-0530.2021.06.012.LIU Jianfeng, YU Hongyi, DU Jianping, et al. Specific emitter identification under dynamic noise based on domain adaptation[J]. Journal of Signal Processing, 2021, 37(6): 1000–1007. doi: 10.16798/j.issn.1003-0530.2021.06.012. [35] ZHENG Yanan, YING Wenwei, HONG Shaohua, et al. A method for cross-receiver specific emitter identification based on CBAM-CNN-BDA[C]. 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Dali, China, 2022: 1320–1324. doi: 10.1109/ICCASIT55263.2022.9987240. [36] YANG Haifen, ZHANG Hao, WANG Houjun, et al. A novel approach for unlabeled samples in radiation source identification[J]. Journal of Systems Engineering and Electronics, 2022, 33(2): 354–359. doi: 10.23919/JSEE.2022.000037. [37] LONG Mingsheng, CAO Yue, WANG Jianmin, et al. Learning transferable features with deep adaptation networks[C]. 32nd International Conference on Machine Learning, Lille, France, 2015: 97–105. [38] 史萌恺. 跨接收机辐射源个体识别方法研究[D]. 郑州: 战略支援部队信息工程大学, 2021. doi: 10.27188/d.cnki.gzjxu.2021.000048.SHI Mengkai. Research on cross-receiver specific emitter identification method[D]. Zhengzhou: PLA Strategic Support Force Information Engineering University, 2021. doi: 10.27188/d.cnki.gzjxu.2021.000048. [39] 郭梁. 基于迁移学习的辐射源识别技术研究[D]. 成都: 电子科技大学, 2021. doi: 10.27005/d.cnki.gdzku.2021.004912.GUO Liang. Research on special emitter identification technology based on transfer learning[D]. Chengdu: University of Electronic Science and Technology of China, 2021. doi: 10.27005/d.cnki.gdzku.2021.004912. [40] CHANG C, HSIEH C, CHIANG C, et al. Domain-specific batch normalization for unsupervised domain adaptation[C]. CVPR, 2019: 7354–7362. [41] WANG Tianchi, YU Lu, WANG Wenyu, et al. Specific emitter identification based on the multi-discrepancy deep adaptation network[J]. IET Radar, Sonar & Navigation, 2022, 16(12): 2079–2088. doi: 10.1049/rsn2.12318. [42] WU Dongming, SHI Junpeng, LI Zhihui, et al. Contrastive semi-supervised learning with pseudo-label for radar signal automatic modulation recognition[J]. IEEE Sensors Journal, 2024, 24(19): 30399–30411. doi: 10.1109/JSEN.2024.3439704. [43] 郑博元, 丛迅超, 胡超, 等. 自监督双流融合的小样本雷达辐射源识别方法[J]. 电讯技术, 2023, 63(9): 1340–1347. doi: 10.20079/j.issn.1001-893x.230426006.ZHENG Boyuan, CONG Xunchao, HU Chao, et al. Few-shot radar emitter identification based on self-supervised dual-stream fusion[J]. Telecommunication Engineering, 2023, 63(9): 1340–1347. doi: 10.20079/j.issn.1001-893x.230426006. [44] MACKEY S, ZHAO Tianya, WANG Xuyu, et al. Cross-domain adaptation for RF fingerprinting using prototypical networks[C]. 20th ACM Conference on Embedded Networked Sensor Systems, Boston, USA, 2022: 812–813. doi: 10.1145/3560905.3568100. [45] CHEN Jun, WONG W K, and HAMDAOUI B. Unsupervised contrastive learning for robust RF device fingerprinting under time-domain shift[C]. IEEE International Conference on Communications, Denver, USA, 2024: 3567–3572. doi: 10.1109/ICC51166.2024.10622173. [46] LING Qing, YAN Wenjun, ZHANG Yuchen, et al. Transfer learning method for specific emitter identification based on pseudo-labelling and meta-learning[J]. IET Radar, Sonar & Navigation, 2024, 18(9): 1460–1473. doi: 10.1049/rsn2.12579. [47] WEI Haojie, FANG Min, LI Haixiang, et al. Prototype-based dual-alignment of multi-source domain adaptation for radar emitter recognition[J]. Signal Processing, 2025, 230: 109853. doi: 10.1016/j.sigpro.2024.109853. [48] YE Yalan, WANG Chunji, DONG Hai, et al. Cross-session specific emitter identification using adversarial domain adaptation with Wasserstein distance[C]. 2022 26th International Conference on Pattern Recognition (ICPR), Montreal, Canada, 2022: 3119–3124. doi: 10.1109/ICPR56361.2022.9956207. [49] 朱佳明, 姚光乐, 王琛, 等. 电台辐射源个体识别的无监督域自适应方法[J]. 电子信息对抗技术, 2025, 40(3): 41–50. doi: 10.3969/j.issn.1674-2230.2025.03.006.ZHU Jiaming, YAO Guangle, WANG Chen, et al. Unsupervised domain adaptive method for specific emitter identification of radio[J]. Electronic Information Warfare Technology, 2025, 40(3): 41–50. doi: 10.3969/j.issn.1674-2230.2025.03.006. [50] WANG Yong, SHU Zhehao, FENG Yinzhi, et al. Enhancing cross-domain remote sensing scene classification by multi-source subdomain distribution alignment network[J]. Remote Sensing, 2025, 17(7): 1302. doi: 10.3390/rs17071302. [51] LIU Jiaxu, WANG Jiao, HUANG Hao, et al. Multi-scale iterative domain adaptation for specific emitter identification[J]. Applied Intelligence, 2024, 54(8): 6299–6318. doi: 10.1007/s10489-024-05484-0. [52] 李林, 俞璐, 蒋曾辉, 等. 基于类特征对齐的多源域适应辐射源个体识别方法[J]. 通信技术, 2023, 56(10): 1137–1145. doi: 10.3969/j.issn.1002-0802.2023.10.003.LI Lin, YU Lu, JIANG Zenghui, et al. Special emitter identification based on multi-source domain adaptation using category feature alignment[J]. Communications Technology, 2023, 56(10): 1137–1145. doi: 10.3969/j.issn.1002-0802.2023.10.003. [53] ZHANG Jingbo, LIU Qingshuo, AN Shaoqian, et al. Cross-domain few-shot specific emitter identification via contrastive self-supervised learning[J]. IEEE Communications Letters, 2025, 29(7): 1564–1568. doi: 10.1109/LCOMM.2025.3568388. [54] YANG Jian, ZHU Shaoxian, WEN Zhongyi, et al. Cross-receiver radio frequency fingerprint identification: A source-free adaptation approach[J]. Sensors, 2025, 25(14): 4451. doi: 10.3390/s25144451. [55] LI Ziying, FU Xiongjun, DONG Jian, et al. Radar signal sorting via graph convolutional network and semi-supervised learning[J]. IEEE Signal Processing Letters, 2025, 32: 421–425. doi: 10.1109/LSP.2024.3519884. [56] ZHANG Xixi, WANG Yu, HUANG Hao, et al. Few-shot automatic modulation classification using architecture search and knowledge transfer in radar–communication coexistence scenarios[J]. IEEE Internet of Things Journal, 2024, 11(19): 32067–32078. doi: 10.1109/JIOT.2024.3423018. [57] BASHA N, HAMDAOUI B, SIVANESAN K, et al. Channel-resilient deep-learning-driven device fingerprinting through multiple data streams[J]. IEEE Open Journal of the Communications Society, 2023, 4: 118–133. doi: 10.1109/OJCOMS.2022.3233372. [58] MOHANTI S, SOLTANI N, SANKHE K, et al. AirID: Injecting a custom RF fingerprint for enhanced UAV identification using deep learning[C]. 2020 IEEE Global Communications Conference, Taipei, China, 2020: 1–6. doi: 10.1109/GLOBECOM42002.2020.9322561. [59] RESTUCCIA F, D’ORO S, AL-SHAWABKA A, et al. DeepFIR: Channel-robust physical-layer deep learning through adaptive waveform filtering[J]. IEEE Transactions on Wireless Communications, 2021, 20(12): 8054–8066. doi: 10.1109/TWC.2021.3089878. [60] D’ORO S, RESTUCCIA F, and MELODIA T. Can you fix my neural network? Real-time adaptive waveform synthesis for resilient wireless signal classification[C]. 2021 IEEE International Conference on Computer Communications, Vancouver, Canada, 2021: 1–10. doi: 10.1109/INFOCOM42981.2021.9488865. [61] SOLTANI N, SANKHE K, DY J, et al. More is better: Data augmentation for channel-resilient RF fingerprinting[J]. IEEE Communications Magazine, 2020, 58(10): 66–72. doi: 10.1109/MCOM.001.2000180. [62] SHEN Guanxiong, ZHANG Junqing, 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. doi: 10.1109/TIFS.2023.3266626. [63] GONG Jialiang, XU Xiaodong, and LEI Yingke. Unsupervised specific emitter identification method using radio-frequency fingerprint embedded InfoGAN[J]. IEEE Transactions on Information Forensics and Security, 2020, 15: 2898–2913. doi: 10.1109/TIFS.2020.2978620. [64] 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. doi: 10.12000/JR19115.SUN Liting, HUANG Zhitao, WANG Xiang, et al. Overview of radio frequency fingerprint extraction in specific emitter identification[J]. Journal of Radars, 2020, 9(6): 1014–1031. doi: 10.12000/JR19115. [65] GANIN Y, USTINOVA E, AJAKAN H, et al. Domain-adversarial training of neural networks[J]. The Journal of Machine Learning Research, 2016, 17(1): 2096–2030. [66] 黄颖坤, 金炜东, 颜康, 等. 基于距离特征的雷达辐射源信号识别方法[J]. 系统仿真学报, 2021, 33(12): 2959–2966. doi: 10.16182/j.issn1004731x.joss.21-FZ0808.HUANG Yingkun, JIN Weidong, YAN Kang, et al. Radar emitter signal identification via distance features[J]. Journal of System Simulation, 2021, 33(12): 2959–2966. doi: 10.16182/j.issn1004731x.joss.21-FZ0808. [67] 史亚, 张文博, 朱明哲, 等. 雷达辐射源个体识别综述[J]. 电子与信息学报, 2022, 44(6): 2216–2229. doi: 10.11999/JEIT210161.SHI Ya, ZHANG Wenbo, ZHU Mingzhe, et al. Specific radar emitter identification: A comprehensive review[J]. Journal of Electronics & Information Technology, 2022, 44(6): 2216–2229. doi: 10.11999/JEIT210161. [68] 崔邦彦, 田润澜, 王东风, 等. 基于注意力机制和改进CLDNN的雷达辐射源识别[J]. 系统工程与电子技术, 2021, 43(5): 1224–1231. doi: 10.12305/j.issn.1001-506X.2021.05.09.CUI Bangyan, TIAN Runlan, WANG Dongfeng, et al. Radar emitter identification based on attention mechanism and improved CLDNN[J]. Systems Engineering and Electronics, 2021, 43(5): 1224–1231. doi: 10.12305/j.issn.1001-506X.2021.05.09. [69] 刘钊, 马爽, 张梦杰, 等. 多径条件下的雷达辐射源个体识别方法[J]. 电子学报, 2023, 51(6): 1654–1665. doi: 10.12263/DZXB.20220990.LIU Zhao, MA Shuang, ZHANG Mengjie, et al. Radar specific emitter identification method under multipath conditions[J]. Acta Electronica Sinica, 2023, 51(6): 1654–1665. doi: 10.12263/DZXB.20220990. [70] 张立民, 谭凯文, 闫文君, 等. 基于多级跳线残差网络的雷达辐射源识别[J]. 系统工程与电子技术, 2022, 44(7): 2148–2156. doi: 10.12305/j.issn.1001-506X.2022.07.10.ZHANG Limin, TAN Kaiwen, YAN Wenjun, et al. Radar emitter recognition based on multi-level jumper residual network[J]. Systems Engineering and Electronics, 2022, 44(7): 2148–2156. doi: 10.12305/j.issn.1001-506X.2022.07.10. [71] 张涛涛, 谢钧, 乔平娟. 基于多源无监督域适应的辐射源个体识别方法[J]. 计算机与现代化, 2025(3): 45–51. doi: 10.3969/j.issn.1006-2475.2025.03.007.ZHANG Taotao, XIE Jun, and QIAO Pingjuan. Specific emitter identification method based on multi-source unsupervised domain adaptation[J]. Computer and Modernization, 2025(3): 45–51. doi: 10.3969/j.issn.1006-2475.2025.03.007. [72] PENG Xingchao, BAI Qinxun, XIA Xide, et al. Moment matching for multi-source domain adaptation[C]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019: 1406–1415. doi: 10.1109/ICCV.2019.00149. [73] AWASTHI A K, GAROV A K, SHARMA M, et al. GNN model based on node classification forecasting in social network[C]. 2023 International Conference on Artificial Intelligence and Smart Communication (AISC), Greater Noida, India, 2023: 1039–1043. doi: 10.1109/AISC56616.2023.10085118. [74] WEN Xiaomin, FANG Shengliang, and FAN Youchen. Reconstruction of radio environment map based on multi-source domain adaptive of graph neural network for regression[J]. Sensors, 2024, 24(8): 2523. doi: 10.3390/s24082523. [75] AL-SHAWABKA A, RESTUCCIA F, D’ORO S, et al. Exposing the fingerprint: Dissecting the impact of the wireless channel on radio fingerprinting[C]. 2020 IEEE Conference on Computer Communications, Toronto, Canada, 2020: 646–655. doi: 10.1109/INFOCOM41043.2020.9155259. [76] 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, 2023, 12(1): 214–234. doi: 10.12000/JR22140.CHEN Xiang, WANG Liandong, XU Xiong, et al. A review of radio frequency fingerprinting methods based on raw I/Q and deep learning[J]. Journal of Radars, 2023, 12(1): 214–234. doi: 10.12000/JR22140. [77] SANKHE K, BELGIOVINE M, ZHOU Fan, et al. ORACLE: Optimized radio classification through convolutional neural networks[C]. 2019 IEEE Conference on Computer Communications, Paris, France, 2019: 370–378. doi: 10.1109/INFOCOM.2019.8737463. [78] HANNA S, KARUNARATNE S, and CABRIC D. WiSig: A large-scale WiFi signal dataset for receiver and channel agnostic RF fingerprinting[J]. IEEE Access, 2022, 10: 22808–22818. doi: 10.1109/ACCESS.2022.3154790. [79] ELMAGHBUB A and HAMDAOUI B. LoRa device fingerprinting in the wild: Disclosing RF data-driven fingerprint sensitivity to deployment variability[J]. IEEE Access, 2021, 9: 142893–142909. doi: 10.1109/ACCESS.2021.3121606. [80] B. B. C, A. Deshmukh and A. V. Narasimhadhan, "Modulation and signal class labelling with active learning and classification using machine learning," 2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Bangalore, India, 2022, pp. 1-5, doi: 10.1109 /CONECCT55679.2022.9865826. [81] FADUL M K M, REISING D R, WEERASENA L P, et al. Improving RF-DNA fingerprinting performance in an indoor multipath environment using semi-supervised learning[J]. IEEE Transactions on Information Forensics and Security, 2024, 19: 3194–3209. doi: 10.1109/TIFS.2024.3360851. [82] SOLTANI N, REUS-MUNS G, SALEHI B, et al. RF fingerprinting unmanned aerial vehicles with non-standard transmitter waveforms[J]. IEEE Transactions on Vehicular Technology, 2020, 69(12): 15518–15531. doi: 10.1109/TVT.2020.3042128. [83] SHEN Guanxiong, ZHANG Junqing, MARSHALL A, et al. Towards scalable and channel-robust radio frequency fingerprint identification for LoRa[J]. IEEE Transactions on Information Forensics and Security, 2022, 17: 774–787. doi: 10.1109/TIFS.2022.3152404. [84] SHEN Guanxiong, ZHANG Junqing, MARSHALL A, et al. Towards receiver-agnostic and collaborative radio frequency fingerprint identification[J]. IEEE Transactions on Mobile Computing, 2024, 23(7): 7618–7634. doi: 10.1109/TMC.2023.3340039. [85] UZUNDURUKAN E, DALVEREN Y, and KARA A. A database for the radio frequency fingerprinting of Bluetooth devices[J]. Data, 2020, 5(2): 55. doi: 10.3390/data5020055. [86] 俞宁宁, 毛盛健, 周成伟, 等. DroneRFa: 用于侦测低空无人机的大规模无人机射频信号数据集[J]. 电子与信息学报, 2024, 46(4): 1147–1156. doi: 10.11999/JEIT230570.YU Ningning, MAO Shengjian, ZHOU Chengwei, et al. DroneRFa: A large-scale dataset of drone radio frequency signals for detecting low-altitude drones[J]. Journal of Electronics & Information Technology, 2024, 46(4): 1147–1156. doi: 10.11999/JEIT230570. [87] 任俊宇, 俞宁宁, 周成伟, 等. DroneRFb-DIR: 用于非合作无人机个体识别的射频信号数据集[J]. 电子与信息学报, 2025, 47(3): 573–581. doi: 10.11999/JEIT240804.REN Junyu, YU Ningning, ZHOU Chengwei, et al. DroneRFb-DIR: An RF signal dataset for non-cooperative drone individual identification[J]. Journal of Electronics and Information Technology, 2025, 47(3): 573–581. doi: 10.11999/JEIT240804. [88] JANG H, YANG W, KIM H, et al. MOANA: Multi-radar dataset for maritime odometry and autonomous navigation application[EB/OL]. https://doi.org/10.48550/arXiv.2412.03887, 2024. [89] ZENG Miyi, YAO Yue, LIU Hong, et al. A specific emitter identification system design for crossing signal modes in the air traffic control radar beacon system and wireless devices[J]. Sensors, 2023, 23(20): 8576. doi: 10.3390/s23208576. [90] ULLAH N, KHAN J A, DE FALCO I, et al. Explainable artificial intelligence: Importance, use domains, stages, output shapes, and challenges[J]. ACM Computing Surveys, 2025, 57(4): 94. doi: 10.1145/3705724. [91] TU Yu, LIN Yun, HOU Changbo, et al. Complex-valued networks for automatic modulation classification[J]. IEEE Transactions on Vehicular Technology, 2020, 69(9): 10085–10089. doi: 10.1109/TVT.2020.3005707. [92] TU Ya, LIN Yun, ZHA Haoran, et al. Large-scale real-world radio signal recognition with deep learning[J]. Chinese Journal of Aeronautics, 2022, 35(9): 35–48. doi: 10.1016/j.cja.2021.08.016. [93] 桂冠, 陶梦圆, 王诚, 等. 面向特定辐射源识别的小样本学习方法综述[J]. 南通大学学报(自然科学版), 2023, 22(3): 1–16. doi: 10.12194/j.ntu.20220928001.GUI Guan, TAO Mengyuan, WANG Cheng, et al. Survey of few-shot learning methods for specific emitter identification[J]. Journal of Nantong University (Natural Science Edition), 2023, 22(3): 1–16. doi: 10.12194/j.ntu.20220928001. [94] 李杰然. 基于盒维数的灵巧噪声干扰识别方法[J]. 海军航空大学学报, 2022, 37(2): 191–195. doi: 10.7682/j.issn.2097-1427.2022.02.005.LI Jieran. Method of smart noise jamming recognition based on box dimension[J]. Journal of Naval Aviation University, 2022, 37(2): 191–195. doi: 10.7682/j.issn.2097-1427.2022.02.005. [95] 杨淑媛, 杨晨, 冯志玺, 等. 电磁目标表征: 知识-数据联合驱动新范式[J]. 航空兵器, 2024, 31(2): 17–31. doi: 10.12132/ISSN.1673-5048.2024.0065.YANG Shuyuan, YANG Chen, FENG Zhixi, et al. A new paradigm for knowledge-data driven electromagnetic target representation[J]. Aero Weaponry, 2024, 31(2): 17–31. doi: 10.12132/ISSN.1673-5048.2024.0065. [96] 张茜茜, 王禹, 林云, 等. 基于深度学习的自动调制识别方法综述[J]. 无线电通信技术, 2022, 48(4): 697–710. doi: 10.3969/j.issn.1003-3114.2022.04.017.ZHANG Xixi, WANG Yu, LIN Yun, et al. A comprehensive survey of deep learning-based automatic modulation recognition methods[J]. Radio Communications Technology, 2022, 48(4): 697–710. doi: 10.3969/j.issn.1003-3114.2022.04.017. [97] XU Huali, ZHI Shuaifeng, SUN Shuzhou, et al. Deep learning for cross-domain few-shot visual recognition: A survey[J]. ACM Computing Surveys, 2025, 57(8): 215. doi: 10.1145/3718362. -
图(2) / 表(9)
计量
- 文章访问数:
- HTML全文浏览量:
- PDF下载量:
- 被引次数: 0
