A modulation recognition model driven by lightweight knowledge distillation in the complex number domain

WANG Ziheng; ZHANG Xu; GAO Shuo; ZHOU Jin

doi:10.11959/j.issn.1000-0801.2025173

您当前的位置：

首页 >

文章列表页 >

A modulation recognition model driven by lightweight knowledge distillation in the complex number domain

Research and Development | 更新时间：2025-09-04

- A modulation recognition model driven by lightweight knowledge distillation in the complex number domain
- Telecommunications Science Vol. 41, Issue 8, Pages: 163-175(2025)
- 作者机构：
  
  天津财经大学理工学院，天津 300222
- 作者简介：
- 基金信息：
  
  Tianjin Natural Science Foundation of China(22JCYBJC01550)
- DOI：10.11959/j.issn.1000-0801.2025173
  CLC： TP393
- Received：01 December 2024，
  
  Revised：2025-02-27，
  
  Accepted：19 March 2025，
  
  Published：20 August 2025
- 稿件说明：
移动端阅览
王子恒,张徐,高硕等.一种复数域轻量化知识蒸馏驱动的调制识别模型[J].电信科学,2025,41(08):163-175.

WANG Ziheng,ZHANG Xu,GAO Shuo,et al.A modulation recognition model driven by lightweight knowledge distillation in the complex number domain[J].Telecommunications Science,2025,41(08):163-175.
王子恒,张徐,高硕等.一种复数域轻量化知识蒸馏驱动的调制识别模型[J].电信科学,2025,41(08):163-175. DOI： 10.11959/j.issn.1000-0801.2025173.

WANG Ziheng,ZHANG Xu,GAO Shuo,et al.A modulation recognition model driven by lightweight knowledge distillation in the complex number domain[J].Telecommunications Science,2025,41(08):163-175. DOI： 10.11959/j.issn.1000-0801.2025173.

摘要

深度学习模型在调制识别任务中依赖大量训练样本，但实际场景中信号样本有限，尤其在复杂噪声环境下，模型性能受限。为此，提出了一种基于局部特征引导的轻量化调制识别方法。首先，构建轻量化教师网络以提取含噪调制信号的局部特征，并设计局部语义特征优化算法将局部知识蒸馏给学生网络；其次，针对调制信号频谱的复数域特性，设计复数域Transformer作为学生网络进行全局特征提取，并最终完成识别任务。实验结果表明，所提模型在小样本场景下相比其他深度学习模型具有更高的识别效率，在计算复杂度和实时性等方面较现有方法表现出明显优势。

Abstract

Deep learning models rely on a large number of training samples in the modulation recognition task. However

in actual scenarios

the signal samples are limited

especially in complex noise environments

where the model performance is restricted. Therefore

a lightweight modulation recognition method based on local feature guidance was proposed. Firstly

a lightweight teacher network was constructed to extract local features from noisy modulated signals

and a local semantic feature optimization algorithm was designed to distill local knowledge into the student network. Secondly

aiming at the complex-domain characteristics of the modulated signal spectrum

a complex-domain Transformer was designed as the student network for global feature extraction

ultimately completing the recognition task. Experimental results show that the proposed model demonstrates higher recognition efficiency in small-sample scenarios compared with other deep learning models

and exhibits significant advantages in terms of computational complexity and real-time performance compared with existing methods.

关键词

Keywords

references

袁莉芬 , 宁暑光 , 何怡刚 , 等 . 基于高阶累积量特征学习的调制识别方法 [J ] . 系统工程与电子技术 , 2019 , 41 ( 9 ): 2122 - 2131 .

YUAN L F , NING S G , HE Y G , et al . Modulation recognition method based on high-order cumulant feature learning [J ] . Systems Engineering and Electronics , 2019 , 41 ( 9 ): 2122 - 2131 .

HUANG S , DAI R , HUANG J J , et al . Automatic modulation classification using gated recurrent residual network [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 8 ): 7795 - 7807 .

党月芳 , 徐启建 , 张杰 , 等 . 高阶累积量和分形理论在信号调制识别中的应用研究 [J ] . 信号处理 , 2013 , 29 ( 6 ): 761 - 765 .

DANG Y F , XU Q J , ZHANG J , et al . Research on modulation classification based on high-order cumulants and fractal theory [J ] . Journal of Signal Processing , 2013 , 29 ( 6 ): 761 - 765 .

查雄 , 彭华 , 秦鑫 , 等 . 基于多端卷积神经网络的调制识别方法 [J ] . 通信学报 , 2019 , 40 ( 11 ): 30 - 37 .

ZHA X , PENG H , QIN X , et al . Modulation recognition method based on multi-inputs convolution neural network [J ] . Journal on Communications , 2019 , 40 ( 11 ): 30 - 37 .

安泽亮 , 张天骐 , 马宝泽 , 等 . 基于一维CNN的多入多出OSTBC信号协作调制识别 [J ] . 通信学报 , 2021 , 42 ( 7 ): 84 - 94 .

AN Z L , ZHANG T Q , MA B Z , et al . Cooperative modulation recognition based on one-dimensional convolutional neural network for MIMO-OSTBC signal [J ] . Journal on Communications , 2021 , 42 ( 7 ): 84 - 94 .

司海飞 , 胡兴柳 , 史震 , 等 . 基于联合特征参数提取的非合作信号调制识别算法 [J ] . 通信学报 , 2020 , 41 ( 7 ): 172 - 185 .

SI H F , HU X L , SHI Z , et al . Non-cooperative signal modulation recognition algorithm based on joint feature parameter extraction [J ] . Journal on Communications , 2020 , 41 ( 7 ): 172 - 185 .

王延坤 , 郭登科 , 马东堂 , 等 . 基于轻量级CNN和信道特征辅助的多用户物理层认证机制 [J ] . 电信科学 , 2023 , 39 ( 11 ): 69 - 79 .

WANG Y K , GUO D K , MA D T , et al . Multi-user physical layer authentication mechanism based on lightweight CNN and channel feature assistance [J ] . Telecommunications Science , 2023 , 39 ( 11 ): 69 - 79 .

CAI J J , GAN F M , CAO X H , et al . Signal modulation classification based on the transformer network [J ] . IEEE Transactions on Cognitive Communications and Networking , 2022 , 8 ( 3 ): 1348 - 1357 .

ZHENG Q H , ZHAO P H , WANG H J , et al . Fine-grained modulation classification using multi-scale radio transformer with dual-channel representation [J ] . IEEE Communications Letters , 2022 , 26 ( 6 ): 1298 - 1302 .

MA W X , CAI Z R , WANG C . A transformer and convolution-based learning framework for automatic modulation classification [J ] . IEEE Communications Letters , 2024 , 28 ( 6 ): 1392 - 1396 .

HOU D B , LI L X , LIN W S , et al . ClST: a convolutional transformer framework for automatic modulation recognition by knowledge distillation [J ] . IEEE Transactions on Wireless Communications , 2024 , 23 ( 7 ): 8013 - 8028 .

HAN K , WANG Y H , CHEN H T , et al . A survey on vision transformer [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 1 ): 87 - 110 .

江沸菠 , 彭于波 , 董莉 . 面向6G的深度图像语义通信模型 [J ] . 通信学报 , 2023 , 44 ( 3 ): 198 - 208 .

JIANG F B , PENG Y B , DONG L . Deep image semantic communication model for 6G [J ] . Journal on Communications , 2023 , 44 ( 3 ): 198 - 208 .

FAN Z M , HU W , GUO H , et al . Hardware and algorithm co-optimization for pointwise convolution and channel shuffle in ShuffleNet V2 [C ] // Proceedings of the 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC) . Piscataway : IEEE Press , 2021 : 3212 - 3217 .

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 .

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 .

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 .

程风云 , 周金 . 信号增强网络驱动的调制识别 [J ] . 电信科学 , 2024 , 40 ( 4 ): 139 - 150 .

CHENG F Y , ZHOU J . Modulation recognition driven by signal enhancement [J ] . Telecommunications Science , 2024 , 40 ( 4 ): 139 - 150 .

ZHOU Q , JING X J , HE Y , et al . LSTM-based automatic modulation classification [C ] // Proceedings of the 2020 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) . Piscataway : IEEE Press , 2020 : 1 - 4 .

WU Z L , ZHOU S Y , YIN Z D , et al . Robust automatic modulation classification under varying noise conditions [J ] . IEEE Access , 2017 , 5 : 19733 - 19741 .

TRIARIDIS K , DOUMANIDIS C , CHATZIDIAMANTIS N D , et al . MM-Net: a multi-modal approach toward automatic modulation classification [J ] . IEEE Communications Letters , 2023 , 28 ( 2 ): 328 - 331 .

ZHANG Q C , JI H B , LI L , et al . Automatic modulation recognition of unknown interference signals based on graph model [J ] . IEEE Wireless Communications Letters , 2024 , 13 ( 9 ): 2317 - 2321 .

AN T T , LEE B M . Robust automatic modulation classification in low signal to noise ratio [J ] . IEEE Access , 2023 , 11 : 7860 - 7872 .

Views

444

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An automatic modulation recognition network based on multi-channel lightweighting

A review on intelligent recognition for digital modulation types

Research on network intrusion detection based on fusion Transformer and Inception

Related Author

WAN Jinhua

SHANG Junna

ZHANG Huadi

Liu Xinqun

Wang Lulu

Qin Shan

Li Baoguo

Li Zerun

Related Institution

The 36th Research Institute, China Electronics Technology Group Corporation

School of Communication Engineering, Hangzhou Dianzi University

College of Electronic Science, National University of Defense Technology

Institute for Military Intelligence Research, Academy of Military Science

College of Information Network Security, People’s Public Security University of China

⁰