基于双曲状态空间模型的无线电信号调制识别

王冠淳; 刘淳; 张向荣; 陈亦凡; 张天扬; 唐旭

doi:10.12263/DZXB.20251225

您当前的位置：

首页 >

文章列表页 >

基于双曲状态空间模型的无线电信号调制识别

学术论文 | 更新时间：2026-05-28

- 基于双曲状态空间模型的无线电信号调制识别
- Research on Radio Signal Modulation Recognition Based on Hyperbolic State Space Model
- 电子学报 2026年54卷第2期页码：517-531
- 作者机构：
  
  西安电子科技大学人工智能学院，陕西西安 710126
- 作者简介：
  
  [ "王冠淳男，1997年12月出生于陕西省咸阳市。分别于2019年和2024年获西安电子科技大学学士、博士学位。现为西安电子科技大学助理研究员。主要研究方向为目标智能解译。中国电子学会会员编号：E190186536M。E-mail: wangguanchun@xidian.edu.cn" ]
  [ "刘淳男，2002年6月出生于陕西省西安市。2024年毕业于西安邮电大学数据科学与大数据技术系，现为西安电子科技大学硕士研究生。主要研究方向为信号智能处理。 E-mail: 24181214479@stu.xidian.edu.cn" ]
  [ "张向荣女，1978年3月出生于陕西省宝鸡市。分别于1999年、2003年和2006年获西安电子科技大学学士、硕士、博士学位。现为西安电子科技大学教授。主要研究方向为机器学习。 E-mail: xrzhang@mail.xidian.edu.cn" ]
  [ "陈亦凡男，2001年4月出生于浙江省金华市。2023年毕业于浙江师范大学智能科学与技术专业，现为西安电子科技大学博士研究生。主要研究方向为信号智能解译。中国电子学会会员编号：E190186539A。 E-mail: yifanchen@stu.xidian.edu.cn" ]
  [ "张天扬男，1996年1月出生于河南省洛阳市。分别于2018年和2023年获西安电子科技大学学士、博士学位，现为西安电子科技大学讲师。主要研究方向为场景分类、目标解译等。中国电子学会会员编号：E190186530M。 E-mail: zhangtianyang@xidian.edu.cn" ]
  [ "唐旭男，1985年1月出生于陕西省西安市。分别于2007年、2010年和2017年获得西安电子科技大学学士、硕士、博士学位，现为西安电子科技大学教授。主要研究方向为目标智能解译。中国电子学会会员编号：E190160631M。E-mail: tangxu128@gmail.com" ]
- 基金信息：
  
  国家自然科学基金(62506285;62501433;62571387;62276197);陕西省自然科学基础研究计划(2025JC-YBQN-795);中国博士后科学基金(2025T180431;2025M771550)
- DOI：10.12263/DZXB.20251225
  中图分类号： TN911.72;TP183
- 收稿：2026-01-18，
  
  录用：2026-02-13，
  
  纸质出版：2026-02-25
- 稿件说明：
移动端阅览
王冠淳, 刘淳, 张向荣, 等. 基于双曲状态空间模型的无线电信号调制识别[J]. 电子学报, 2026, 54(02): 517-531.

WANG Guanchun, LIU Chun, ZHANG Xiangrong, et al. Research on Radio Signal Modulation Recognition Based on Hyperbolic State Space Model[J]. Acta Electronica Sinica, 2026, 54(02): 517-531.
王冠淳, 刘淳, 张向荣, 等. 基于双曲状态空间模型的无线电信号调制识别[J]. 电子学报, 2026, 54(02): 517-531. DOI：10.12263/DZXB.20251225

WANG Guanchun, LIU Chun, ZHANG Xiangrong, et al. Research on Radio Signal Modulation Recognition Based on Hyperbolic State Space Model[J]. Acta Electronica Sinica, 2026, 54(02): 517-531. DOI：10.12263/DZXB.20251225

摘要

无线通信系统利用接收信号的数据特性进行自动调制识别（Automatic Modulation Recognition，AMR）是确保电磁频谱智能监测与管控的重要先导步骤。近年来，深度学习技术凭借其强大的隐式特征提取能力被广泛研究，国内外学者致力于探索深度学习技术在信号调制识别任务中的潜力，并已提出一系列AMR方法，依据其采用的网络架构可粗略划分为以下三种类型：基于卷积神经网络（Convolutional Neural Networks，CNN）、基于循环神经网络（Recurrent Neural Networks，RNN）以及基于Transformer网络的方法。然而，在动态复杂电磁环境中，现有AMR方法面临两大共性挑战：现有深度学习模型对时变信道噪声缺乏自适应感知能力，导致不同信噪比（Signal-to-Noise Ratio，SNR）条件下的不同调制类型之间易产生混淆；现有模型在长时序信号建模中的计算效率与特征提取能力难以兼顾，对长序列信号数据的判别精度受限。因此，针对现有调制识别方法缺乏电磁环境感知能力、长时序高效建模能力不足等问题，本文将状态空间模型（State Space Models，SSMs）的长序列建模能力与双曲几何空间的SNR感知特性相结合，提出一种基于双曲状态空间模型（Hyperbolic state space model，H-Mamba）的无线电信号调制识别方法。具体地，本文首先建立了一种基于状态空间模型的时频特征挖掘机制（Mamba-based Time-frequency Feature Mining，MTFM），联合提取时域与频域判别性表征以增强不同调制类型信号间可分性；其次，从双曲几何空间的角度提出了一种新颖的信号质量感知方法，依据所接收信号的双曲几何半径判断其SNR分布情况，并基于此设计了一种基于双曲SNR提示的特征调制模块（Hyperbolic SNR-aware Feature Modulation，HSFM），通过双曲几何引导动态调整信号表征，提升模型对不同SNR条件的适应能力；最后，提出了一种基于双曲SNR感知的课程学习策略（Hyperbolic SNR-aware Curriculum Learning，HSCL），通过双曲距离度量实现对样本质量差异的感知，从而动态调整模型训练过程以缓解低质数据干扰。实验结果表明：本文方法在RML2016A（RadioML2016.10A）、RML2016B（RadioML2016.10B）以及RML2018（RadioML2018）等多个公开信号调制识别数据集上均取得最优性能，较现有最优方法分别提高了4.09%、1.58%、1.21%，证明了其有效性。

Abstract

In wireless communication systems

automatic modulation recognition (AMR) leveraging the intrinsic characteristics of received signals serves as a crucial prerequisite for intelligent electromagnetic spectrum monitoring and management. In recent years

deep learning technology has been widely studied due to its powerful implicit feature representation capabilities. Many scholars have explored the potential of deep learning technology in signal modulation recognition tasks and have proposed a series of AMR methods

which can be roughly divided into three types based on their network architecture: convolutional neural networks-based (CNN)

recurrent neural networks-based (RNN)

and Transformer-based methods. However

in dynamic and complex electromagnetic environments

existing AMR methods face two common challenges: existing models typically lack adaptive perception capabilities for time-varying channel noise

leading to confusion between different modulation types under varying signal-to-noise ratio (SNR) conditions; existing models struggle to balance computational efficiency and representation capabilities in long-term signal modeling

limiting the accuracy of discrimination for long-sequence signals. Considering existing modulation recognition methods typically lack the capabilities of electromagnetic environment perception and struggle to efficiently model long-term time sequences

this paper proposes a novel hyperbolic state space model (H-Mamba) that integrates the long-sequence modeling capability of state space models (SSMs) with the SNR awareness inherent in hyperbolic geometry. Specifically

we first develop a Mamba-based time-frequency feature mining (MTFM) mechanism to jointly extract discriminative representations from both time and frequency domains

thereby enhancing inter-class separability among different modulation types. Next

we introduce a novel signal quality perception method from the perspective of hyperbolic geometry that correlates the hyperbolic radius of a received signal with its SNR distribution. Building upon this insight

we design a hyperbolic SNR-aware feature modulation (HSFM) module that dynamically adjusts signal representations under hyperbolic geometric guidance

improving model robustness across varying SNR conditions. Furthermore

we propose a hyperbolic SNR-aware curriculum learning (HSCL) strategy that leverages hyperbolic distance to perceive sample quality differences

enabling adaptive training dynamics that mitigate the adverse impact of low-quality data. Extensive experiments on multiple public AMR benchmarks

including RadioML2016.10A (RML2016A)

RadioML2016.10B (RML2016B)

RadioML2018 (RML2018)

demonstrate that the proposed H-Mamba achieves state-of-the-art performance

outperforming current best baselines by 4.09%

1.58%

and 1.21%

respectively

thereby validating its efficacy.

关键词

Keywords

references

徐冬月 , 田蕴哲 , 陈康 , 等 . 面向信号调制识别的对抗攻击与防御综述 [J ] . 计算机研究与发展 , 2025 , 62 ( 7 ): 1713 - 1737 .

Xu Dongyue , Tian Yunzhe , Chen Kang , et al . Survey on adversarial attack and defense for signal modulation recognition [J ] . Journal of Computer Research and Development , 2025 , 62 ( 7 ): 1713 - 1737 . (in Chinese)

杨伟超 , 杜宇 , 文伟 , 等 . 基于多重分形谱智能分析的卫星信号调制识别研究 [J ] . 电子学报 , 2022 , 50 ( 6 ): 1336 - 1343 . DOI: 10.12263/DZXB.20210882 http://dx.doi.org/10.12263/DZXB.20210882

Yang Weichao , Du Yu , Wen Wei , et al . Modulation recognition of satellite communication signal based on intelligent analysis of multi-fractal spectrum [J ] . Acta Electronica Sinica , 2022 , 50 ( 6 ): 1336 - 1343 . (in Chinese) . DOI: 10.12263/DZXB.20210882 http://dx.doi.org/10.12263/DZXB.20210882

李钦 , 刘伟 , 牛朝阳 , 等 . 低SNR下基于分裂EfficientNet网络的雷达信号调制方式识别 [J ] . 电子学报 , 2023 , 51 ( 3 ): 675 - 686 .

Li Qin , Liu Wei , Niu Chaoyang , et al . Radar signal modulation recognition based on split EfficientNet under low signal-to-noise ratio [J ] . Acta Electronica Sinica , 2023 , 51 ( 3 ): 675 - 686 . (in Chinese)

李昱 , 石晓然 , 苗昊倩 , 等 . 基于DETR_S的卫星信号智能检测方法 [J ] . 电子学报 , 2025 , 53 ( 5 ): 1365 - 1378 .

Li Yi , Shi Xiaoran , Miao Haoqian , et al . Intelligent detection method of satellite signal based on DETR_S [J ] . Acta Electronica Sinica , 2025 , 53 ( 5 ): 1365 - 1378 . (in Chinese)

张俊林 , 王彬 , 汪洋 , 等 . 一种α稳定分布噪声下OFDM信号调制识别与参数估计算法 [J ] . 电子学报 , 2018 , 46 ( 6 ): 1390 - 1396 .

Zhang Junlin , Wang Bin , Wang Yang , et al . An algorithm for recognition and parameters estimation of OFDM in alpha stable distribution noise [J ] . Acta Electronica Sinica , 2018 , 46 ( 6 ): 1390 - 1396 . (in Chinese)

查雄 , 彭华 , 秦鑫 , 等 . 基于循环神经网络的卫星幅相信号调制识别与解调算法 [J ] . 电子学报 , 2019 , 47 ( 11 ): 2443 - 2448 . DOI: 10.3969/j.issn.0372-2112.2019.11.029 http://dx.doi.org/10.3969/j.issn.0372-2112.2019.11.029

Zha Xiong , Peng Hua , Qin Xin , et al . Satellite amplitude-phase signals modulation identification and demodulation algorithm based on the cyclic neural network [J ] . Acta Electronica Sinica , 2019 , 47 ( 11 ): 2443 - 2448 . (in Chinese) . DOI: 10.3969/j.issn.0372-2112.2019.11.029 http://dx.doi.org/10.3969/j.issn.0372-2112.2019.11.029

李东瑾 , 杨瑞娟 , 李晓柏 , 等 . 基于核协同表示与鉴别投影的辐射源调制识别 [J ] . 电子学报 , 2020 , 48 ( 9 ): 1695 - 1702 .

Li Dongjin , Yang Ruijuan , Li Xiaobai , et al . Emitter signal modulation recognition based on kernel collaborative representation and discriminative projection [J ] . Acta Electronica Sinica , 2020 , 48 ( 9 ): 1695 - 1702 . (in Chinese)

Wang G C , Liu Z Y , Zhang X R , et al . PID: A parameter-efficient isolation domain-incremental learning framework for signal modulation classification [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2026 , 37 ( 3 ): 1449 - 1462 . DOI: 10.1109/tnnls.2025.3615307 http://dx.doi.org/10.1109/tnnls.2025.3615307

Zhang X R , Chen Y F , Wang G C , et al . EDDA: An efficient divide-and-conquer domain adapter for automatics modulation recognition [J ] . IEEE Journal of Selected Topics in Signal Processing , 2025 , 19 ( 1 ): 140 - 153 . DOI: 10.1109/jstsp.2024.3453559 http://dx.doi.org/10.1109/jstsp.2024.3453559

Zhu D M , Mathews V J , Detienne D H . A likelihood-based algorithm for blind identification of QAM and PSK signals [J ] . IEEE Transactions on Wireless Communications , 2018 , 17 ( 5 ): 3417 - 3430 . DOI: 10.1109/twc.2018.2811802 http://dx.doi.org/10.1109/twc.2018.2811802

Hazza A , Shoaib M , Alshebeili S A , et al . An overview of feature-based methods for digital modulation classification [C ] // 2013 1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA) . Piscataway : IEEE , 2013 : 1 - 6 . DOI: 10.1109/iccspa.2013.6487244 http://dx.doi.org/10.1109/iccspa.2013.6487244

LeCun Y , Bengio Y , Hinton G . Deep learning [J ] . Nature , 2015 , 521 ( 7553 ): 436 - 444 . DOI: 10.1038/nature14539 http://dx.doi.org/10.1038/nature14539

He K M , Zhang X Y , Ren S Q , et al . Deep residual learning for image recognition [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2016 : 770 - 778 . DOI: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90

Hirschberg J , Manning C D . Advances in natural language processing [J ] . Science , 2015 , 349 ( 6245 ): 261 - 266 . DOI: 10.1126/science.aaa8685 http://dx.doi.org/10.1126/science.aaa8685

O’Shea T J , Corgan J , Clancy T C . Convolutional radio modulation recognition networks [M ] // Engineering applications of neural networks . Cham : Springer , 2016 : 213 - 226 . DOI: 10.1007/978-3-319-44188-7_16 http://dx.doi.org/10.1007/978-3-319-44188-7_16

Hermawan A P , Ginanjar R R , Kim D S , et al . CNN-based automatic modulation classification for beyond 5G communications [J ] . IEEE Communications Letters , 2020 , 24 ( 5 ): 1038 - 1041 . DOI: 10.1109/lcomm.2020.2970922 http://dx.doi.org/10.1109/lcomm.2020.2970922

Xiao C H , Yang S Y , Feng Z X . Complex-valued depthwise separable convolutional neural network for automatic modulation classification [J ] . IEEE Transactions on Instrumentation and Measurement , 2023 , 72 : 2522310 . DOI: 10.1109/tim.2023.3298657 http://dx.doi.org/10.1109/tim.2023.3298657

Zhang J W , Wang T T , Feng Z X , et al . Toward the automatic modulation classification with adaptive wavelet network [J ] . IEEE Transactions on Cognitive Communications and Networking , 2023 , 9 ( 3 ): 549 - 563 . DOI: 10.1109/tccn.2023.3252580 http://dx.doi.org/10.1109/tccn.2023.3252580

Hong D H , Zhang Z L , Xu X D . Automatic modulation classification using recurrent neural networks [C ] // 2017 3rd IEEE International Conference on Computer and Communications . Piscataway : IEEE , 2017 : 695 - 700 . DOI: 10.1109/compcomm.2017.8322633 http://dx.doi.org/10.1109/compcomm.2017.8322633

Njoku J N , Morocho-Cayamcela M E , Lim W . CGDNet: Efficient hybrid deep learning model for robust automatic modulation recognition [J ] . IEEE Networking Letters , 2021 , 3 ( 2 ): 47 - 51 . DOI: 10.1109/lnet.2021.3057637 http://dx.doi.org/10.1109/lnet.2021.3057637

Xu J L , Luo C B , Parr G , et al . A spatiotemporal multi-channel learning framework for automatic modulation recognition [J ] . IEEE Wireless Communications Letters , 2020 , 9 ( 10 ): 1629 - 1632 . DOI: 10.1109/lwc.2020.2999453 http://dx.doi.org/10.1109/lwc.2020.2999453

Zhang F X , Luo C B , Xu J L , et al . An efficient deep learning model for automatic modulation recognition based on parameter estimation and transformation [J ] . IEEE Communications Letters , 2021 , 25 ( 10 ): 3287 - 3290 . DOI: 10.1109/lcomm.2021.3102656 http://dx.doi.org/10.1109/lcomm.2021.3102656

Zhang J W , Wang T T , Feng Z X , et al . AMC-net: An effective network for automatic modulation classification [C ] // ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2023 : 1 - 5 . DOI: 10.1109/icassp49357.2023.10097070 http://dx.doi.org/10.1109/icassp49357.2023.10097070

Li W H , Deng W , Wang K R , et al . A complex-valued transformer for automatic modulation recognition [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 12 ): 22197 - 22207 . DOI: 10.1109/jiot.2024.3379429 http://dx.doi.org/10.1109/jiot.2024.3379429

Yi Z R , Meng H , Gao L , et al . Efficient convolutional dual-attention transformer for automatic modulation recognition [J ] . Applied Intelligence , 2025 , 55 ( 3 ): 231 . DOI: 10.1007/s10489-024-06202-6 http://dx.doi.org/10.1007/s10489-024-06202-6

Chen Z H , Zhang X Z , He K . Multi-channel convolutional distilled transformer for automatic modulation classification [C ] // 2024 International Joint Conference on Neural Networks . Piscataway : IEEE , 2024 : 1 - 8 . DOI: 10.1109/ijcnn60899.2024.10650112 http://dx.doi.org/10.1109/ijcnn60899.2024.10650112

GU A , DAO T . Mamba: Linear-time sequence modeling with selective state spaces [C ] // First Conference on Language Modeling , Philadelphia : OpenReview.net , 2024 : 1 - 32 .

GU A , GOEL K , RE C . Efficiently modeling long sequences with structured state spaces [C ] // International Conference on Learning Representations , Virtual Event : OpenReview.net , 2022 : 1 - 27 .

GU A , JOHNSON I , GOEL K , et al . Combining recurrent, convolutional, and continuous-time models with linear state space layers [J ] . Advances in neural information processing systems , 2021 , 34 : 572 - 585 .

杜文亮 , 许晓宇 , 赵佳琦 , 等 . 基于共享提示与Mamba适配器的遥感图像文本检索方法 [J ] . 电子学报 , 2025 , 53 ( 9 ): 3358 - 3370 .

Du Wenliang , Xu Xiaoyu , Zhao Jiaqi , et al . A remote sensing image text retrieval method based on the shared prompt and mamba adapter [J ] . Acta Electronica Sinica , 2025 , 53 ( 9 ): 3358 - 3370 . (in Chinese)

Cannon J W , Floyd W J , Kenyon R , et al . Hyperbolic geometry [J ] . Flavors of Geometry , 1997 , 31 ( 59-115 ): 2 .

O’shea T J , West N . Radio machine learning dataset generation with gnu radio [C ] // Proceedings of the GNU Radio Conference . Boulder : GNU Radio , 2016 , 1 ( 1 ): 12 - 17 .

O’Shea T J , Roy T , Clancy T C . Over-the-air deep learning based radio signal classification [J ] . IEEE Journal of Selected Topics in Signal Processing , 2018 , 12 ( 1 ): 168 - 179 . DOI: 10.1109/jstsp.2018.2797022 http://dx.doi.org/10.1109/jstsp.2018.2797022

Loshchilov I , Hutter F . Decoupled weight decay regularization [C ] // International Conference on Learning Representations , Vancouver : OpenReview.net , 2018 : 1 - 18 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

STAR-RIS辅助的CR-SWIPT系统安全波束成形算法

基于学习的能量采集认知M2M通信资源分配算法

分布式协作频谱感知网络中恶意节点检测和定位方法研究

认知无线电网络路由研究综述

基于大模型的RAG算法的快速评估系统：RGE-Pipeline