Automatic modulation recognition based on deep learning for wireless communication systems

ZHANG Yuntao; SHAO Yufeng; LONG Xi; MIN Zhehao; WU Tong; CUI Mengqi; ZHUO Zhimin; LAN Jia; CHEN Guogan; WANG Anrong; ZHANG Yanlu; KUANG Fuhao; XU Zhanduo; XIANG Hongjin; JIA Lansi; ZHANG Xu

doi:10.11959/j.issn.1000-0801.DXKX260213

Chinese

您当前的位置：

首页 >

文章列表页 >

Automatic modulation recognition based on deep learning for wireless communication systems

更新时间：2026-06-17

- Automatic modulation recognition based on deep learning for wireless communication systems
- Telecommunications Science (2026)
- 作者机构：
  
  1.嘉兴大学信息科学与工程学院，浙江嘉兴 314001
  2.嘉兴大学全省多模态感知与智能系统重点实验室（信息科学与工程学院），浙江嘉兴 314001
  3.重庆三峡科技大学电子与信息工程学院，重庆 404100
  4.南京农业大学智慧农业学院（人工智能学院），江苏南京 210031
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(61107064);2025 Zhejiang Provincial Key Graduate Education Reform Project(JGZD2025080);2023 Shanghai Collaborative Innovation Project(XTCX-KJ-2023-64);Jiaxing City Science and Technology Public Welfare Project(2024AY10023);Major Horizontal Research Project of Jiaxing University(00525098);Research Start-up Project of Jiaxing University(70524009);Key Horizontal Research Project of Jiaxing University(00524097)
- DOI：10.11959/j.issn.1000-0801.DXKX260213
  CLC： TN929
- Received：05 April 2026，
  
  Revised：2026-06-15，
  
  Accepted：17 June 2026，
- 稿件说明：
移动端阅览
ZHANG Yuntao, SHAO Yufeng, LONG Xi, et al. Automatic modulation recognition based on deep learning for wireless communication systems[J/OL]. Telecommunications Science, 2026.
DOI：

ZHANG Yuntao, SHAO Yufeng, LONG Xi, et al. Automatic modulation recognition based on deep learning for wireless communication systems[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260213.

摘要

自动调制识别（automatic modulation recognition，AMR）是一种在无先验信息或非合作场景下，自动判断接收信号调制方式的技术，能广泛应用于频谱感知、干扰管理等通信领域。传统的AMR依赖人工特征设计，存在计算复杂度高和部署灵活性差等问题。近年来，深度学习（deep learning，DL）技术通过端到端学习可从原始信号中自动提取信号特征，能有效提升信号调制方式的识别精度，引起了业界广泛关注。顺应这一发展态势，从信号表示、模型结构、数据集评测和挑战展望四个方面综述了深度学习型AMR技术的研究进展，分析了卷积神经网络（convolutional neural network，CNN）、循环神经网络（recurrent neural network，RNN）、Transformer及其混合模型的适用场景、性能优势与应用瓶颈，并探讨了如何适配低信噪比（signal-to-noise ratio，SNR）情形与满足高鲁棒性、跨场景泛化、降低标注数据依赖性和轻量化边缘部署等实际应用需求。

Abstract

Automatic modulation recognition (AMR) is a technique that automatically identifies the modulation type of received signals in scenarios without prior information or in non-cooperative environments. It can be widely applied in communication fields such as spectrum sensing and interference management. Traditional AMR methods rely on manually designed features

which leads to high computational complexity and limited deployment flexibility. In recent years

deep learning (DL) techniques have attracted extensive attention because signal features can be automatically extracted from raw signals through end-to-end learning

thereby effectively improving modulation recognition accuracy. In response to this development trend

the research progress of deep learning-based AMR techniques was reviewed from four aspects: signal representation

model architecture

dataset evaluation

and challenges and prospects. The applicable scenarios

performance advantages

and application bottlenecks of convolutional neural networks (CNNs)

recurrent neural networks (RNNs)

Transformers

and their hybrid models were analyzed. In addition

the adaptability of these methods to low signal-to-noise ratio (SNR) conditions was discussed

together with practical requirements such as high robustness

cross-scenario generalization

reduced dependence on labeled data

and lightweight edge deployment.

关键词

Keywords

references

赵亚军，郁光辉，徐汉青 . 6G 移动通信网络：愿景、挑战与关键技术 [J ] . 中国科学：信息科学， 2019 ， 49 （ 8 ）： 963 - 987 .

ZHAO Y J , YU G H , XU H Q . 6G mobile communication network: vision, challenge and key technologies [J ] . Scientia Sinica Informationis , 2019 , 49 ( 8 ): 963 - 987 .

MAO Q , HU F , HAO Q . Deep learning for intelligent wireless networks: a comprehensive survey [J ] . IEEE Communications Surveys & Tutorials , 2018 , 20 ( 4 ): 2595 - 2621 .

WEI W , MENDEL J M . Maximum-likelihood classification for digital amplitude-phase modulations [J ] . IEEE Transactions on Communications , 2000 , 48 ( 2 ): 189 - 193 .

彭华甫，江桦，裴立业，等 . 基于瞬时幅度特征的连续相位调制信号识别 [J ] . 太赫兹科学与电子信息学报， 2013 ， 6 （ 11 ）： 948 - 952 .

PENG H F , JIANG H , PEI L Y , et al . Recognition of continuous phase modulation signals based on instantaneous amplitude features [J ] . Journal of Terahertz Science and Electronic Information Technology , 2013 , 6 ( 11 ): 948 - 952 .

TAN X , XIE Z , YUAN X , et al . Small sample signal modulation recognition based on higher-order cumulants and CatBoost [C ] // Proceedings of the 2022 7th International Conference on Communication, Image and Signal Processing (CCISP) . Chengdu, China , 2022 : 324 - 329 .

ZHAO Y H , YING Z B , WANG Y J , et al . Boosting automatic modulation recognition in wireless communications with frequency encoder [J ] . IEEE Transactions on Cognitive Communications and Networking , 2025 , 11 ( 4 ): 2135 - 2148 .

张顺，龚怡宏，王进军，等 . 深度卷积神经网络的发展及其在计算机视觉领域的应用 [J ] . 计算机学报， 2019 ， 42 （ 3 ）： 453 - 482 .

ZHANG S , GONG Y H , WANG J J , et al . The development of deep convolutional neural networks and their applications in computer vision [J ] . Chinese Journal of Computers , 2019 , 42 ( 3 ): 453 - 482 .

ZANG K , WU W Q , LUO W , et al . Deep sparse learning for automatic modulation classification using recurrent neural networks [J ] . Sensors , 2021 , 21 ( 19 ): 6410 .

ZHANG F , LUO C , XU J , et al . An efficient deep learning model for automatic modulation recognition based on parameter estimation and transformation [J ] . IEEE Communications Letters , 2021 , 25 : 3287 - 3290 .

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 .

ZHANG X X , WANG Y , LIN Y , et al . A review of automatic modulation recognition methods based on deep learning [J ] . Radio Communications Technology , 2022 , 48 ( 4 ): 697 - 710 .

WANG B , YUAN Z , LI A P , et al . Hybrid-driven model fusing deep learning and knowledge for automatic modulation recognition [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 10 ): 13934 - 13945 .

O'SHEA T J , CORGAN J , CLANCY T C . Convolutional radio modulation recognition networks [C ] // Engineering Applications of Neural Networks . Communications in Computer and Information Science , 2016 , 629 : 213 - 226 .

ZHANG H , HUANG M , YANG J , et al . A data preprocessing method for automatic modulation classification based on CNN [J ] . IEEE Communications Letters , 2020 , 25 ( 4 ): 1206 - 1210 .

SI W J , WAN C X , DENG Z . Intra-pulse modulation recognition of dual-component radar signals based on deep convolutional neural network [J ] . IEEE Communications Letters , 2021 , 25 ( 10 ): 3305 - 3309 .

WANG Y , LIU M , YANG J , et al . Data-driven deep learning for automatic modulation recognition in cognitive radios [J ] . IEEE Transactions on Vehicular Technology , 2019 , 68 ( 6 ): 5690 - 5699 .

龚安，张贵临，牟伟清，等 . 基于多层小波分解卷积神经网络的自动调制识别方法 [J/OL ] . 无线电通信技术， 2024 （网络首发）： 1 - 10 .

GONG A , ZHANG G L , MOU W Q , et al . Automatic modulation recognition method based on multi-layer wavelet decomposition convolutional neural network [J/OL ] . Radio Communications Technology , 2024 (Online first): 1 - 10 .

DUA M , TAILOR A , DUA S , et al . Noise robust multi-carrier modulation recognition using novel integration of STFT-autoencoder and fine-tuned CNN [J ] . IETE Journal of Research , 2025 , 1 - 11 .

PENG S , JIANG H , WANG H , et al . Modulation classification based on signal constellation diagrams and deep learning [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2019 , 30 ( 3 ): 718 - 727 .

ABDULKAREM A M , AL-DULAIMI A , MOHAMMED A H , et al . Robust automatic modulation classification using the continuous wavelet transform and deep convolutional neural network [J ] . Computers , 2022 , 11 ( 11 ): 162 .

UTRILLA R , FONSECA E , ARAUJO A , et al . Gated recurrent unit neural networks for automatic modulation classification with resource-constrained end-devices [J ] . IEEE Access , 2020 , 8 : 112783 - 112794 .

CHENG R J , CHEN Q , HUANG M . Automatic modulation recognition using deep CVCNN-LSTM architecture [J ] . Alexandria Engineering Journal , 2024 , 104 : 162 - 170 .

ZHANG H , NIE R H , LIN M H , et al . A deep learning based algorithm with multi-level feature extraction for automatic modulation recognition [J ] . Wireless Networks , 2021 , 27 ( 7 ): 4665 - 4676 .

ZANG K , MA Z G . Automatic modulation classification based on hierarchical recurrent neural networks with grouped auxiliary memory [J ] . IEEE Access , 2020 , 8 : 213052 - 213061 .

ZHANG F X , LUO C B , XU J L , et al . Deep learning based automatic modulation recognition: models, datasets, and challenges [J ] . Digital Signal Processing , 2022 , 129 : 103650 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C ] // Advances in Neural Information Processing Systems , December 04, 2017 , Long Beach, USA . Red Hook, NY : Curran Associates Inc , 2017 : 5998 - 6008 .

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 .

ZHANG W N , XUE K L , YAO A Q , et al . CTRNet: an automatic modulation recognition based on transformer-CNN neural network [J ] . Electronics , 2024 , 13 ( 17 ): 3408 .

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

ZHANG X Q , LUO Z Q , XIAO W S , et al . Deep learning-based modulation recognition for MIMO systems: fundamental, methods, challenges [J ] . IEEE Access , 2024 , 12 : 112558 - 112575 .

WANG X , ZHAO Y , HUANG Z . A survey of deep transfer learning in automatic modulation classification [J ] . IEEE Transactions on Cognitive Communications and Networking , 2025 , 11 ( 3 ): 1357 - 1381 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Polar codes decoding algorithm based on convolutional neural network

Key technology research and model validation of text classification system based on deep learning

Research on multi-level fusion localization mechanisms in cell-free integrated sensing and communication systems

Research on log text fault association rule mining based on GPT network

Infrared image human vehicle detection algorithm based on SDL-YOLO

Related Author

Rui GUO

Fanchun RAN

Shaomin WANG

Di YANG

Hua REN

Pei Rongkang

Wang Jie

Li Jiamin

Related Institution

School of Information Science and Engineering, Southeast University

National Mobile Communications Research Laboratory, Southeast University

Faculty of Electrical Engineering and Computer Science, Ningbo University

School of Automotive Engineering, Zhejiang Institute of Communications

School of Automobile, Chang'an University

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰