基于无损VMD和Mamba的小样本辐射源识别方法

何文龙; 陈剑; 尹宝鑫; 毛浩阳; 贾杰; 王兴伟

doi:10.12263/DZXB.20260405

您当前的位置：

首页 >

文章列表页 >

基于无损VMD和Mamba的小样本辐射源识别方法

射频计算 | 更新时间：2026-10-16

- 基于无损VMD和Mamba的小样本辐射源识别方法
- Few-Shot Specific Emitter Identification Method Based on Lossless VMD and Mamba
- 电子学报 2026年54卷第6期页码：2509-2521
- 作者机构：
  
  东北大学计算机科学与工程学院，辽宁沈阳 110169
- 作者简介：
  
  何文龙男，2004年4月出生于湖南省岳阳市。现为东北大学计算机科学与工程学院硕士研究生。主要研究方向为辐射源识别技术及应用。E-mail: hewl@mails.neu.edu.cn
  陈剑男，1980年9月出生于湖南省邵阳市。现为东北大学计算机科学与工程学院教授、博士生导师。主要研究方向为智能可重构表面、设备到设备通信以及信号与图像处理。E-mail: chenjian@mail.neu.edu.cn
  尹宝鑫男，1999年8月出生于吉林省延边朝鲜族自治州。现为东北大学计算机科学与工程学院博士研究生。主要研究方向为无线通信、信号与处理及其应用。E-mail: yinbx1@mails.neu.edu.cn
  毛浩阳男，2006年2月出生于湖南省邵阳市。现为东北大学计算机科学与工程学院本科生。主要研究方向为辐射源识别技术及其应用。E-mail: ueerscgg@icloud.com
  贾杰女，1980年10月出生于辽宁省鞍山市。现为东北大学计算机科学与工程学院教授、博士生导师。主要研究方向为异构网络、物联网和认知无线电网络。E-mail: jiajie@mail.neu.edu.cn
  王兴伟男，1968年1月出生于内蒙古自治区包头市。现为东北大学计算机科学与工程学院教授、博士生导师。主要研究方向为云计算、未来网络等。E-mail: wangxw@mail.neu.edu.cn
- 基金信息：
  
  国家自然科学基金(62132004;62572109;62572113);航空科学基金(20230026050001);辽宁省中央引导地方科技发展专项资金项目(2025JH6/101100009);沈阳市中青年科技创新领军人才项目(RC231173);沈阳市科技计划项目(23-503-6-17)
- DOI：10.12263/DZXB.20260405
  中图分类号： TN911.7;
- 收稿：2026-04-26，
  
  录用：2026-05-16，
  
  纸质出版：2026-06-25
- 稿件说明：
移动端阅览
何文龙, 陈剑, 尹宝鑫, 等. 基于无损VMD和Mamba的小样本辐射源识别方法[J]. 电子学报, 2026, 54(06): 2509-2521.

HE Wenlong, CHEN Jian, YIN Baoxin, et al. Few-Shot Specific Emitter Identification Method Based on Lossless VMD and Mamba[J]. Acta Electronica Sinica, 2026, 54(06): 2509-2521.
何文龙, 陈剑, 尹宝鑫, 等. 基于无损VMD和Mamba的小样本辐射源识别方法[J]. 电子学报, 2026, 54(06): 2509-2521. DOI：10.12263/DZXB.20260405

HE Wenlong, CHEN Jian, YIN Baoxin, et al. Few-Shot Specific Emitter Identification Method Based on Lossless VMD and Mamba[J]. Acta Electronica Sinica, 2026, 54(06): 2509-2521. DOI：10.12263/DZXB.20260405

摘要

随着无线通信技术的快速发展，无线通信辐射源数量呈现出指数级增长态势，电磁环境日益复杂，频谱资源日趋紧张。在这一背景下，如何在海量的设备中实现精准的身份识别与安全接入，已成为关乎社会稳定与经济发展的核心议题。传统的身份认证方式依赖协议层或应用层的数字凭证，存在易被窃取、伪造或攻击等安全漏洞。相比之下，基于射频指纹（Radio Frequency Fingerprinting，RFF）的特定辐射源识别技术（Specific Emitter Identification，SEI）作为一种物理层的安全手段，具有广阔应用前景。该技术通过提取发射机硬件电路中固有的物理缺陷进行身份认证，具有天然的唯一性与长期稳定性。然而，现有基于深度学习的通信辐射源识别方法普遍面临对标注数据依赖性强、泛化能力不足、长序列信号处理效率低等的挑战。为此，本文重点聚焦小样本条件下通信辐射源的高效识别问题，提出了一种基于自监督学习的低复杂度识别算法。首先，针对原始I/Q信号中指纹特征易被信道噪声和调制信息掩盖的问题，本文引入了无损的变分模态分解（Variational Mode Decomposition，VMD）方法，通过自适应地将原始I/Q信号转换为多个本征模态函数分量，增强了指纹特征的表示能力；其次，为克服传统序列建模模型在处理长序列信号时的二次计算复杂度瓶颈，本文引入了具有线性计算复杂度的Mamba架构，并构建了一个基于Mamba线性流编码器的自监督网络模型，利用大规模辅助数据集进行预训练，结合对比学习和监督学习，促使模型学习具有强判别性的通用特征表示；最后，针对实际应用中新增设备样本稀缺和存在未知干扰的问题，本文采用了迁移学习策略，利用少量的目标域辐射源样本微调一个轻量级线性分类器，以快速适应具体的下游分类任务。在WiSig数据集上的仿真实验结果表明，本文所提出的方法在6-way 1-shot场景下识别准确率达到91.20%，在显著降低了计算复杂度与样本集规模依赖的同时保持了较高的识别性能，具有良好的现实应用前景。

Abstract

With the rapid development of wireless communication technology

the number of wireless communication emitters has grown exponentially

leading to an increasingly complex electromagnetic environment and increasingly scarce spectrum resources. Against this backdrop

achieving precise identity recognition and secure access among massive devices has become a critical issue concerning social stability and economic development. Traditional identity authentication methods rely on digital credentials at the protocol or application layer

which are susceptible to theft

forgery

or attacks. In contrast

the specific emitter identification (SEI) technology based on radio frequency fingerprinting (RFF) serves as a physical-layer security measure with broad application prospects. This technology authenticates identities by extracting the inherent physical imperfections in the emitter’s hardware circuits

offering natural uniqueness and long-term stability. However

existing deep learning-based methods for communication emitter identification generally face challenges

including heavy reliance on labeled data

limited generalization

and low efficiency in processing long-sequence signals. To address these issues

this paper focuses on the efficient identification of communication emitters under few-shot conditions and proposes a low-complexity self-supervised recognition algorithm. First

to overcome the problem that fingerprint features in the original I/Q signals are easily obscured by channel noise and modulation information

this paper introduces a lossless variational mode decomposition (VMD) method. This approach adaptively converts the original I/Q signals into multiple intrinsic mode function components

enhancing the representational capacity of fingerprint features. Second

to address the quadratic computational complexity bottleneck of traditional sequence modeling methods when processing long-sequence signals

this paper incorporates the Mamba architecture

which has linear computational complexity. A self-supervised network model based on the Mamba linear flow encoder is constructed

utilizing a large-scale auxiliary dataset for pre-training. By integrating contrastive and supervised learning

the model is guided to learn discriminative

generalizable feature representations. Finally

to tackle the scarcity of new device samples and the presence of unknown interference in practical applications

this paper employs a transfer learning strategy. Using a small number of target-domain emitter samples

a lightweight linear classifier is fine-tuned to adapt to specific downstream classification tasks quickly. Simulation results on the WiSig dataset show that the proposed method achieves 91.20% accuracy in a 6-way 1-shot scenario. While significantly reducing computational complexity and dependence on sample size

the method maintains high recognition performance

demonstrating promising potential for real-world applications.

关键词

Keywords

references

Talbot K I , Duley P R , Hyatt M H . Specific emitter identification and verification [J ] . Technology Review Journal , 2003 , 11 ( 1 ): 113 - 133 .

刘高辉 , 席宏恩 . 改进变分模态分解与多特征的通信辐射源个体识别方法 [J ] . 电子与信息学报 , 2024 , 46 ( 10 ): 4044 - 4052 .

Liu Gaohui , Xi Hongen . Individual identification method for communication emitters based on improved variational modal decomposition and multiple features [J ] . Journal of Electronics & Information Technology , 2024 , 46 ( 10 ): 4044 - 4052 . (in Chinese)

张振 , 贾济铖 , 康健 , 等 . 射频指纹识别技术方法综述 [J ] . 无线电通信技术 , 2021 , 47 ( 3 ): 249 - 258 .

Zhang Zhen , Jia Jicheng , Kang Jian , et al . Overview of RF fingerprint identification technology methods [J ] . Radio Communications Technology , 2021 , 47 ( 3 ): 249 - 258 . (in Chinese)

秦鑫 , 黄洁 , 查雄 , 等 . 基于扩张残差网络的雷达辐射源信号识别 [J ] . 电子学报 , 2020 , 48 ( 3 ): 456 - 462 .

Qin Xin , Huang Jie , Zha Xiong , et al . Radar emitter signal recognition based on dilated residual network [J ] . Acta Electronica Sinica , 2020 , 48 ( 3 ): 456 - 462 . (in Chinese)

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 .

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 . (in Chinese)

刘旭 , 罗鹏飞 , 李纲 . 基于拟合角特征及SVM的雷达辐射源个体识别 [C ] // 第五届信号和智能信息处理与应用学术会议论文集 . 银川 : 中国高科技产业化研究会 , 2011 : 281 - 284 .

Liu Xu , Luo Pengfei , Li Gang . Radar emitter individual identification based on fitting angle features and SVM [C ] // Proceedings of the 5th Academic Conference on Signal and Intelligent Information Processing and Application . Yinchuan : China High-tech Industrialization Association , 2011 : 281 - 284 . (in Chinese)

梁江海 , 黄知涛 , 袁英俊 , 等 . 一种基于经验模态分解的通信辐射源个体识别方法 [J ] . 中国电子科学研究院学报 , 2013 , 8 ( 4 ): 393 - 397 .

Liang Jianghai , Huang Zhitao , Yuan Yingjun , et al . A method based on empirical mode decomposition for identifying transmitter individuals [J ] . Journal of China Academy of Electronics and Information Technology , 2013 , 8 ( 4 ): 393 - 397 . (in Chinese)

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 . DOI: 10.1109/jstsp.2018.2796446 http://dx.doi.org/10.1109/jstsp.2018.2796446

Roy D , Mukherjee T , Chatterjee M , et al . RFAL: Adversarial learning for RF transmitter identification and classification [J ] . IEEE Transactions on Cognitive Communications and Networking , 2020 , 6 ( 2 ): 783 - 801 . DOI: 10.1109/tccn.2019.2948919 http://dx.doi.org/10.1109/tccn.2019.2948919

Wang Yu , Gui Guan , Lin Yun , et al . Few-shot specific emitter identification via deep metric ensemble learning [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 24 ): 24980 - 24994 . DOI: 10.1109/jiot.2022.3194967 http://dx.doi.org/10.1109/jiot.2022.3194967

Xie Cunxiang , Zhang Limin , Zhong Zhaogen . Few-shot specific emitter identification based on variational mode decomposition and meta-learning [J ] . Wireless Communications and Mobile Computing , 2022 , 2022 : 4481416 . DOI: 10.1155/2022/4481416 http://dx.doi.org/10.1155/2022/4481416 .

Liu Pengfei , Wang Wei , Feng Ziqin , et al . Data-efficient few-shot specific emitter identification using bi-interpolative metric learning [J ] . IEEE Transactions on Information Forensics and Security , 2025 , 20 : 6371 - 6382 . DOI: 10.1109/tifs.2025.3581060 http://dx.doi.org/10.1109/tifs.2025.3581060

Hanna S , Karunaratne S , 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 http://dx.doi.org/10.1109/access.2022.3154790

Dragomiretskiy K , Zosso D . Variational mode decomposition [J ] . IEEE Transactions on Signal Processing , 2014 , 62 ( 3 ): 531 - 544 . DOI: 10.1109/tsp.2013.2288675 http://dx.doi.org/10.1109/tsp.2013.2288675

Liu Hanwen , Huang Yuhe , Gong Yifeng , et al . HyDRA: A hybrid dual-mode network for closed- and open-set RFFI with optimized VMD [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 24 ): 53828 - 53841 . DOI: 10.1109/jiot.2025.3621243 http://dx.doi.org/10.1109/jiot.2025.3621243

Gu A , Dao T . Mamba: Linear-time sequence modeling with selective state spaces [PP/OL ] . V2. arXiv ( 2024-05-31 )[ 2026-04-04 ] . https://doi.org/10.48550/arXiv.2312.00752 https://doi.org/10.48550/arXiv.2312.00752 .

Liu Chao , Fu Xue , Wang Yu , et al . Overcoming data limitations: A few-shot specific emitter identification method using self-supervised learning and adversarial augmentation [J ] . IEEE Transactions on Information Forensics and Security , 2024 , 19 : 500 - 513 . DOI: 10.1109/tifs.2023.3324394 http://dx.doi.org/10.1109/tifs.2023.3324394

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 http://dx.doi.org/10.1109/tvt.2023.3296120

Xu Lai , Zhang Weijie , Tang Tiantian , et al . P3MC: Dual-level data augmentation for robust few-shot specific emitter identification [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 18 ): 38668 - 38679 . DOI: 10.1109/jiot.2025.3586923 http://dx.doi.org/10.1109/jiot.2025.3586923

Van der Maaten L , Hinton G . Visualizing data using t-SNE [J ] . Journal of Machine Learning Research , 2008 , 9 ( 86 ): 2579 - 2605 .

浏览量

181

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

PCDA-MPAT：物理约束数据增强与多径Transformer的无源物联网室内定位方法

基于行为多样性数据增强的RFID手势识别技术

基于层次化掩码图自编码框架的APT威胁检测方法

SM3RNet：一种基于空间Mamba的模态缺失鲁棒病灶分割网络

RIS辅助宽带太赫兹ISAC系统鲁棒保密传输方法