基于深度学习的调制识别综述

doi:10.11959/j.issn.1000-0801.2021114

电信科学 ›› 2021, Vol. 37 ›› Issue (5): 82-90.doi: 10.11959/j.issn.1000-0801.2021114

• 专题：通信与AI融合 • 上一篇下一篇

基于深度学习的调制识别综述

孙姝君¹, 彭盛亮¹, 姚育东², 杨喜³

¹ 华侨大学信息科学与工程学院，福建厦门 361021
² 史蒂文斯理工学院电子与计算机工程系，美国新泽西州霍博肯 07030
³ 吉首大学信息科学与工程学院，湖南吉首 416000

修回日期:2021-05-20 出版日期:2021-05-20 发布日期:2021-05-01
作者简介:孙姝君（1997− ），女，华侨大学信息科学与工程学院硕士生，主要研究方向为无线通信、人工智能
彭盛亮（1982− ），男，博士，华侨大学信息科学与工程学院副教授、硕士生导师，主要研究方向为认知无线电、人工智能、物联网等
姚育东（1960− ），男，博士，史蒂文斯理工学院电子与计算机工程系终身教授。2011年当选国际电气电子工程师协会会士（IEEE Fellow），2015年当选美国国家发明家科学院院士（Fellow of National Academy of Inventors），2017年当选加拿大工程院院士（Fellow of Canadian Academy of Engineering）。主要研究方向为通信信息技术、人工智能、健康物联网
杨喜（1978− ），男，博士，吉首大学信息科学与工程学院教授、硕士生导师，主要研究方向为认知无线电、统计信号处理、智能信息与信号处理
基金资助:
国家自然科学基金资助项目(61861019);华侨大学中央高校基本科研业务费专项(ZQN-708)

A survey of deep learning based modulation recognition

Shujun SUN¹, Shengliang PENG¹, Yudong YAO², Xi YANG³

¹ College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
² Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken NJ 07030, USA
³ College of Information Science and Engineering, Jishou University, Jishou 416000, China

Revised:2021-05-20 Online:2021-05-20 Published:2021-05-01
Supported by:
The National Natural Science Foundation of China(61861019);The Fundamental Research Funds for the Central Universities(ZQN-708)

摘要/Abstract

摘要：

调制识别是通信系统的基础任务之一，在认知无线电、智能通信、无线电监管、电子对抗等领域均有着广泛的应用。近年来，基于深度学习的调制识别技术以其在特征提取和识别性能方面的优势，日益成为研究的焦点。系统地梳理了基于深度学习的调制识别技术，首先介绍了相关基础，随后详细阐述了其系统架构、数据预处理方式、深度神经网络结构、常用数据集以及评价指标，最后分析展望了该技术未来的发展方向。

关键词: 深度学习, 调制识别, 数据预处理, 深度神经网络

Abstract:

Modulation recognition is one of the fundamental tasks for communications systems, which can be widely applied in various fields, such as cognitive radio, intelligent communications, radio surveillance, electronic warfare, etc.In recent years, deep learning (DL) based modulation recognition has attracted great attention due to its superiority in feature extraction and recognition performance.The techniques of DL based modulation recognition were systematically summarized.Firstly, some knowledge relevant to DL based modulation recognition was introduced.Then, the system architecture, data pre-processing methods, deep neural network structures, prevalent datasets and performance metrics of DL based modulation recognition were illustrated.Finally, the future directions of DL based modulation recognition were also discussed.

Key words: deep learning, modulation recognition, data pre-processing, deep neural network

中图分类号:

TN929

孙姝君, 彭盛亮, 姚育东, 杨喜. 基于深度学习的调制识别综述[J]. 电信科学, 2021, 37(5): 82-90.

Shujun SUN, Shengliang PENG, Yudong YAO, Xi YANG. A survey of deep learning based modulation recognition[J]. Telecommunications Science, 2021, 37(5): 82-90.

图/表 3

图1

图2

表1

参考文献 37

[1]	DOBRE O A , ABDI A , BAR-NESS Y ,et al. Survey of automatic modulation classification techniques: classical approaches and new trends[J]. IET Communications, 2007,1(2): 137.
[2]	PENG S L , JIANG H Y , WANG H X ,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.
[3]	PANAGIOTOU P , ANASTASOPOULOS A , POLYDOROS A . Likelihood ratio tests for modulation classification[C]// Proceedings of MILCOM 2000 Proceedings.21st Century Military Communications,Architectures and Technologies for Information Superiority (Cat.No.00CH37155). Piscataway: IEEE Press, 2000: 670-674.
[4]	SHI Q H , KARASAWA Y . Automatic modulation identification based on the probability density function of signal phase[J]. IEEE Transactions on Communications, 2012,60(4): 1033-1044.
[5]	XIE X J , NI Y Q , PENG S L ,et al. Deep learning based automatic modulation classification for varying SNR environment[C]// Proceedings of 2019 28th Wireless and Optical Communications Conference (WOCC). Piscataway: IEEE Press, 2019: 1-5.
[6]	董鑫, 欧阳喜, 袁强 . 多径信道下基于高阶累积量的通信信号调制识别算法[J]. 信息工程大学学报, 2015,16(1): 73-78.
	DONG X , OUYANG X , YUAN Q . Automatic modulation classification using cumulant features for communications via multipath channels[J]. Journal of Information Engineering University, 2015,16(1): 73-78.
[7]	PAWAR S U , DOHERTY J F . Modulation recognition in continuous phase modulation using approximate entropy[J]. IEEE Transactions on Information Forensics and Security, 2011,6(3): 843-852.
[8]	XIE L J , WAN Q . Automatic modulation recognition for phase shift keying signals with compressive measurements[J]. IEEE Wireless Communications Letters, 2018,7(2): 194-197.
[9]	CHIKHA W B , DAYOUB I , HAMOUDA W ,et al. Modulation recognition for MIMO relaying broadcast channels with direct link[J]. IEEE Wireless Communications Letters, 2014,3(1): 50-53.
[10]	XIE L J , WAN Q . Automatic modulation recognition for phase shift keying signals with compressive measurements[J]. IEEE Wireless Communications Letters, 2018,7(2): 194-197.
[11]	KHARBECH S , DAYOUB I , ZWINGELSTEIN-COLIN M ,et al. On classifiers for blind feature-based automatic modulation classification over multiple-input–multiple-output channels[J]. IET Communications, 2016,10(7): 790-795.
[12]	ASLAM M W , ZHU Z C , NANDI A K . Automatic modulation classification using combination of genetic programming and KNN[J]. IEEE Transactions on Wireless Communications, 2012,11(8): 2742-2750.
[13]	GOODFELLOW I J , BENGIO Y , COURVILLE A C . Deep Learning[M]. Massachusetts: MIT Press, 2016.
[14]	LEE J , KIM B , KIM J ,et al. Deep neural network-based blind modulation classification for fading channels[C]// Proceedings of 2017 International Conference on Information and Communication Technology Convergence (ICTC). Piscataway: IEEE Press, 2017: 551-554.
[15]	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.
[16]	HU S S , PEI Y Y , LIANG P P ,et al. Deep neural network for robust modulation classification under uncertain noise conditions[J]. IEEE Transactions on Vehicular Technology, 2020,69(1): 564-577.
[17]	ZHENG S L , QI P H , CHEN S C ,et al. Fusion methods for CNN-based automatic modulation classification[J]. IEEE Access, 2019(7): 66496-66504.
[18]	RAJENDRAN S , MEERT W , GIUSTINIANO D ,et al. Deep learning models for wireless signal classification with distributed low-cost spectrum sensors[J]. IEEE Transactions on Cognitive Communications and Networking, 2018,4(3): 433-445.
[19]	HONG S , ZHANG Y B , WANG Y ,et al. Deep learning-based signal modulation identification in OFDM systems[J]. IEEE Access, 2019(7): 114631-114638.
[20]	MOSSAD O S , ELNAINAY M , TORKI M . Deep convolutional neural network with multi-task learning scheme for modulations recognition[C]// Proceedings of 2019 15th International Wireless Communications ＆ Mobile Computing Conference (IWCMC). Piscataway: IEEE Press, 2019: 1644-1649.
[21]	KHAN F N , ZHONG K P , AL-ARASHI W H ,et al. Modulation format identification in coherent receivers using deep machine learning[J]. IEEE Photonics Technology Letters, 2016,28(17): 1886-1889.
[22]	O’SHEA T J , CORGAN J , CLANCY T C . Convolutional radio modulation recognition networks[C]// Proceedings of Engineering Applications of Neural Networks.[S.l.:s.n.], 2016.
[23]	HUANG S , CHAI L , LI Z N ,et al. Automatic modulation classification using compressive convolutional neural network[J]. IEEE Access, 2019(7): 79636-79643.
[24]	WANG D S , ZHANG M , LI Z ,et al. Modulation format recognition and OSNR estimation using CNN-based deep learning[J]. IEEE Photonics Technology Letters, 2017,29(19): 1667-1670.
[25]	DAVIDSON K L , GOLDSCHNEIDER J R , CAZZANTI L ,et al. Feature-based modulation classification using circular statistics[C]// Proceedings of IEEE MILCOM 2004. Piscataway:IEEE Press, 2004: 765-771.
[26]	MENDIS G J , WEI J , MADANAYAKE A . Deep learning-based automated modulation classification for cognitive radio[C]// Proceedings of2016 IEEE International Conference on Communication Systems (ICCS). Piscataway: IEEE Press, 2016: 1-6.
[27]	MA J T , LIN S C , GAO H J ,et al. Automatic modulation classification under non-Gaussian noise: a deep residual learning approach[C]// Proceedings of ICC 2019 - 2019 IEEE International Conference on Communications (ICC). Piscataway: IEEE Press, 2019: 1-6.
[28]	LI Y B , SHAO G P , WANG B . Automatic modulation classification based on bispectrum and CNN[C]// Proceedings of2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). Piscataway: IEEE Press, 2019: 311-316.
[29]	TU Y , LIN Y . Deep neural network compression technique towards efficient digital signal modulation recognition in edge device[J]. IEEE Access, 2019(7): 58113-58119.
[30]	HINTON G E , OSINDERO S , TEH Y W . A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006,18(7): 1527-1554.
[31]	MENDIS G J , WEI-KOCSIS J , MADANAYAKE A . Deep learning based radio-signal identification with hardware design[J]. IEEE Transactions on Aerospace and Electronic Systems, 2019,55(5): 2516-2531.
[32]	WANG F , WANG Y C , CHEN X . Graphic constellations and DBN based automatic modulation classification[C]// Proceedings of 2017 IEEE 85th Vehicular Technology Conference (VTC Spring). Piscataway: IEEE Press, 2017: 1-5.
[33]	WANG Q , DU P F , YANG J Y ,et al. Transferred deep learning based waveform recognition for cognitive passive radar[J]. Signal Processing, 2019,155: 259-267.
[34]	TANG B , TU Y , ZHANG Z Y ,et al. Digital signal modulation classification with data augmentation using generative adversarial nets in cognitive radio networks[J]. IEEE Access, 2018,6: 15713-15722.
[35]	GREFF K , SRIVASTAVA R K , KOUTNíK J ,et al. LSTM: a search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017,28(10): 2222-2232.
[36]	ZHANG M , ZENG Y , HAN Z D ,et al. Automatic modulation recognition using deep learning architectures[C]// Proceedings of2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). Piscataway:IEEE Press, 2018: 1-5.
[37]	O'SHEA T J , WEST N . Radio machine learning dataset generation with GNU radio[Z]. 2016.

文献	预处理	DNN	候选调制方案	SNR/dB	平均Acc	复杂度
Mendis等^[26]	图像	DBN	4FSK、16QAM、BPSK、QPSK、OFDM	-2～5	94.50%	/
Wang等^[32]	图像	DBN	BPSK、QPSK、8PSK、16QAM	0～10	97.57%	O(N)*
Peng等^[2]	图像	CNN	BPSK、QPSK、OQPSK、8PSK、16QAM、64QAM、4ASK	0～10	84.15%	6.6 ms
					89.00%	18 ms
Li等^[28]	图像	CNN	BPSK、2ASK、2FSK、4FSK、8FSK、LFM、OFDM	-3～10	56.35%	/
Tang等^[34]	图像	CNN	BPSK、4ASK、QPSK、OQPSK、8PSK、16QAM、32QAM、64QAM	-6～14	91.75%	/
		GAN
Tu和Lin^[29]	图像	CNN	4ASK、BSPK、QPSK、OQPSK、8PSK、16QAM、32QAM、64QAM	-6～6	91.70%	19.42 ms
		剪枝CNN			91.00%	6.7 ms
O’Shea等^[15]	序列	CNN	RadioML2018.01a	-20～20	36.50%	/
					42.00%	14 h*
Ma等^[27]	谱图	CNN	BPSK、2ASK、4QAM、8ASK、16QAM	-5～10	66.00%	/
Zheng等^[17]	序列	CNN	BPSK、QPSK、8PSK、OQPSK、2FSK、4FSK、8FSK、16QAM、32QAM、64QAM、4PAM、8PAM	-20～30	53.50%55.00%	//
Hu等^[16]	序列	RNN	BPSK、QPSK、8PSK、16QAM	0～20	79.00%	9.2 ms
Zhang等^[36]	序列	CNN	RadioML2016.10a	-20～18	54.50%	/
	特征	RNN			55.00%	/
Rajendran等^[18]	序列	RNN	RadioML2016.10a	-20～20	56.00%	6.4 MB*
注：O(N)为计算复杂度，14 h为训练时间，6.4 MB为模型大小，其余均为识别时间。

基于深度学习的调制识别综述

A survey of deep learning based modulation recognition

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 3

参考文献 37

相关文章 15

Metrics

推荐阅读 0

[1]	卢敏, 胡娟, 张先超, 丁伟健, 乐光学. 基于用户多特征融合的个性化推荐模型[J]. 电信科学, 2023, 39(5): 101-115.
[2]	卢敏, 秦泽豪, 陈志辉, 张敏, 乐光学. 基于1D-Concatenate的信道估计DNN模型优化方法[J]. 电信科学, 2023, 39(4): 71-86.
[3]	诸葛斌, 尹正虎, 斯文学, 颜蕾, 董黎刚, 蒋献. 基于学生知识追踪的多指标习题推荐算法[J]. 电信科学, 2022, 38(9): 129-143.
[4]	周杰, Esono Mikue Bernardo Esono, 王学英, 周惠婷, 罗宏. 基于SLM-PTS算法融合的NC-OFDM峰均比优化[J]. 电信科学, 2022, 38(7): 63-74.
[5]	高岩, 石坚, 马圣雨, 马柏林, 乐光学. 基于DropBlock双模态混合神经网络的无线通信调制识别[J]. 电信科学, 2022, 38(5): 75-86.
[6]	李攀攀, 谢正霞, 乐光学, 刘鑫. 基于深度学习的无线通信接收方法研究进展与趋势[J]. 电信科学, 2022, 38(2): 1-17.
[7]	申情, 郭文宾, 楼俊钢, 余强国. 考虑多层次潜在特征的个性化推荐模型[J]. 电信科学, 2022, 38(2): 71-83.
[8]	陈志宏, 王明晓. 计算机视觉在智慧安防中的应用[J]. 电信科学, 2021, 37(8): 142-147.
[9]	唐博恒, 柴鑫刚. 基于云边协同的计算机视觉推理机制[J]. 电信科学, 2021, 37(5): 72-81.
[10]	彭双, 王晓东, 彭宗举, 陈芬. 基于深度学习的快速QTMT划分[J]. 电信科学, 2021, 37(4): 73-81.
[11]	胡道允, 齐进, 陆钱春, 李锋, 房红强. 基于深度学习的流量工程算法研究与应用[J]. 电信科学, 2021, 37(2): 107-114.
[12]	张捷, 杨丽花, 王增浩, 呼博, 聂倩. 一种新型的基于深度学习的时变信道预测方法[J]. 电信科学, 2021, 37(1): 39-47.
[13]	李远宁,宁柏锋,董召杰. 电网机巡图像分析框架与深度学习方法[J]. 电信科学, 2020, 36(8): 167-174.
[14]	张婷婷,章坚武,郭春生,陈华华,周迪,王延松,徐爱华. 基于深度学习的图像目标检测算法综述[J]. 电信科学, 2020, 36(7): 92-106.
[15]	郭锐,冉凡春. 基于卷积神经网络的极化码译码算法[J]. 电信科学, 2020, 36(6): 119-124.