基于生成对抗与卷积神经网络的调制识别方法

doi:10.12305/j.issn.1001-506X.2022.03.37

系统工程与电子技术 ›› 2022, Vol. 44 ›› Issue (3): 1036-1043.doi: 10.12305/j.issn.1001-506X.2022.03.37

基于生成对抗与卷积神经网络的调制识别方法

邵凯^1,^2,^3,*, 朱苗苗^1,^2,³, 王光宇^1,^2,³

1. 重庆邮电大学通信与信息工程学院, 重庆 400065
2. 移动通信教育部工程研究中心, 重庆 400065
3. 移动通信技术重庆市重点实验室, 重庆 400065

收稿日期:2021-03-10 出版日期:2022-03-01 发布日期:2022-03-10
通讯作者: 邵凯
作者简介:邵凯(1977—), 男, 副教授, 硕士, 主要研究方向为新型多址接入技术、多载波调制技术|朱苗苗(1996—), 女, 硕士研究生, 主要研究方向为深度学习、调制识别|王光宇(1964—), 男, 教授, 博士, 主要研究方向为新型多址接入技术、多载波调制技术
基金资助:
中国电子科技集团公司第二十九研究所资助课题

Modulation recognition method based on generative adversarial andconvolutional neural network

Kai SHAO^1,^2,^3,*, Miaomiao ZHU^1,^2,³, Guangyu WANG^1,^2,³

1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
2. Engineering Research Center of Mobile Communications of the Ministry of Education, Chongqing 400065, China
3. Chongqing Key Laboratory of Mobile Communications Technology, Chongqing 400065, China

Received:2021-03-10 Online:2022-03-01 Published:2022-03-10
Contact: Kai SHAO

摘要/Abstract

摘要：

自动调制识别在频谱监测和认知无线电中占有重要地位。针对现有调制识别算法在低信噪比条件下识别率低的问题, 提出一种基于生成对抗网络(generative adversarial network, GAN)和卷积神经网络(convolutional neural network, CNN)的数字信号调制识别方法。在利用平滑伪Wigner-Ville分布将调制信号转换为时频图像(time-frequency images, TFIs)后, 在经典GAN中嵌入了剩余密集块(residual dense block, RDB)结构, 保证了对TFIs的去噪和修复。通过对经典的剩余网络(residual network, ResNet)模型微调, 满足了TFIs的识别与分类。仿真结果表明, 所提方法在低信噪比情况下有效地降低了噪声对TFIs的干扰, 提高了识别性能。

关键词: 自动调制识别, 时频分布, 卷积神经网络, 生成对抗网络, 剩余密集块

Abstract:

Automatic modulation recognition occupies an important position in spectrum monitoring and cognitive radio. Aiming at the low recognition rate problem of existing modulation recognition algorithms under the condition of low signal to noise ratio, a digital signal modulation recognition method combined generative adversarial network (GAN) and convolutional neural network (CNN). After using the smooth pseudo Wigner-Ville distribution to convert the modulated signal into time-frequency images (TFIs), the residual dense block (RDB) structure is embeded in the classic GAN network to guarantees the denosing and repairmen of TFIs. By fine-tuning the classic residual networkl (ResNet) model of CNN network, the recognition and classification of TFIs is satisfied. The simulation results show that the proposed method effectively reduces the interference of noise on TFIs and improves the recognition performance under the condition of low signal to noise ratio.

Key words: automatic modulation recognition, time-frequency distribution, convolutional neural network (CNN), generative adversarial network (GAN), residual dense block

中图分类号:

TN911.3

邵凯, 朱苗苗, 王光宇. 基于生成对抗与卷积神经网络的调制识别方法[J]. 系统工程与电子技术, 2022, 44(3): 1036-1043.

Kai SHAO, Miaomiao ZHU, Guangyu WANG. Modulation recognition method based on generative adversarial andconvolutional neural network[J]. Systems Engineering and Electronics, 2022, 44(3): 1036-1043.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

参考文献 21

1	WEI W , MENDEL J . Maximum-likelihood classification for digi- tal amplitude-phase modulations[J]. IEEE Trans.on Communications, 2000, 48 (2): 189- 193. doi: 10.1109/26.823550
2	HAMEED F , DOBRE O , POPESCU D . On the likelihood-based approach to modulation classification[J]. IEEE Trans.on Wireless Communications, 2009, 8 (12): 5884- 5892. doi: 10.1109/TWC.2009.12.080883
3	RAMEZANI A , KIM I , KIM D , et al. Likelihood-based modulation classification for multiple-antenna receiver[J]. IEEE Trans.on Communications, 2013, 61 (9): 3816- 3829. doi: 10.1109/TCOMM.2013.073113.121001
4	HAZAR M , ODABASIOGLU N , ENSARI T , et al. Perfor-mance analysis and improvement of machine learning algorithms for automatic modulation recognition over Rayleigh fading channels[J]. Neural Computer, 2018, 29 (9): 351- 360. doi: 10.1007/s00521-017-3040-6
5	HAN L B , GAO F F , LI Z , et al. Low complexity automatic modulation classification based on order-statistics[J]. IEEE Trans.on Wireless Communications, 2017, 16 (1): 400- 411. doi: 10.1109/TWC.2016.2623716
6	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.
7	XIE W W , HU S , YU C , et al. Deep learning in digital modulation recognition using high order cumulants[J]. IEEE Access, 2019, 7, 63760- 63766. doi: 10.1109/ACCESS.2019.2916833
8	JIN S S, LIN Y, WANG H. Automatic modulation recognition of digital signals based on Fisherface[C]//Proc. of the IEEE International Conference on Software Quality, Reliability and Security Companion, 2017: 216-220.
9	ZHAO H N, ZHOU Y Q, SUN B, et al. Cyclic spectrum based intelligent modulation recognition with machine learning[C]//Proc. of the 10th International Conference on Wireless Communications and Signal Processing, 2018.
10	ZHAO Y L , YU Z M , WAN Z Q , et at . Low complexity OSNR monitoring and modulation format identification based on binarized neural networks[J]. Journal of Lightwave Technology, 2020, 38 (6): 1314- 1322. doi: 10.1109/JLT.2020.2973232
11	QU Z Y , HOU C F , HOU C B , et al. Radar signal intra-pulse modulation recognition based on convolutional neural network and deep Q-Learning network[J]. IEEE Access, 2020, 8, 49125- 49136. doi: 10.1109/ACCESS.2020.2980363
12	ZHANG J , LI Y , YIN J P . Modulation classification method for frequency modulation signals based on the time-frequency distribution and CNN[J]. IET Radar, Sonar & Navigation, 2017, 12 (2): 244- 249.
13	BAI J L, GAO L, GAO J P, et al. A new radar signal modulation recognition algorithm based on time-frequency transform[C]// Proc. of the IEEE 4th International Conference on Signal and Image Processing, 2019: 21-25.
14	ZHANG M , DIAO M , GUO L M . Convolutional neural networks for automatic cognitive radio waveform recognition[J]. IEEE Access, 2017, 5, 11074- 11082. doi: 10.1109/ACCESS.2017.2716191
15	李红光, 郭英, 眭萍, 等. 基于时频特征的卷积神经网络跳频调制识别[J]. 浙江大学学报(工学版), 2020, 54 (10): 1945- 1954.
	LI H G , GUO Y , MU P , et al. Frequency hopping modulation recognition of convolutional neural network based on time-frequency characteristics[J]. Journal of Zhejiang University (Engineering Science), 2020, 54 (10): 1945- 1954.
16	GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proc. of the International Conference on Neural Information Processing Systems, 2014: 2672-2680.
17	CHI J N , WU C D , YU X S , et al. Single low-dose CT image denoising using a generative adversarial network with modified U-net generator and multi-level discriminator[J]. IEEE Access, 2020, 8, 133470- 133487. doi: 10.1109/ACCESS.2020.3006512
18	LI D L , GONG S H , NIU S L , et al. Image blind denoising using a generative adversarial network for LED chip visual locali- zation[J]. IEEE Sensors Journal, 2020, 20 (12): 6582- 6595. doi: 10.1109/JSEN.2020.2976576
19	ZENG Y , ZHANG M , HAN F , et al. Spectrum analysis and convolutional neural network for automatic modulation recognition[J]. IEEE Wireless Communications Letters, 2019, 8 (3): 929- 932. doi: 10.1109/LWC.2019.2900247
20	ZHANG Y L, TIAN Y P, KONG Y, et al. Residual dense network for image super-resolution[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 2472-2481.
21	HE K M, ZHANG X Y, REN S Q, et al. Deep residual lear-ning for image recognition[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.

[1]	宋爽, 张悦, 张琳娜, 岑翼刚, 李浥东. 基于深度学习的轻量化目标检测算法[J]. 系统工程与电子技术, 2022, 44(9): 2716-2725.
[2]	王彩云, 吴钇达, 王佳宁, 马璐, 赵焕玥. 基于改进的CNN和数据增强的SAR目标识别[J]. 系统工程与电子技术, 2022, 44(8): 2483-2487.
[3]	刘戎翔, 吴琳, 谢智歌, 刘虹麟. 基于生成对抗网络的防空体系态势辅助分析[J]. 系统工程与电子技术, 2022, 44(8): 2522-2529.
[4]	韦娟, 杨皇卫, 宁方立. 基于NMF与CNN联合优化的声学场景分类[J]. 系统工程与电子技术, 2022, 44(5): 1433-1438.
[5]	徐平亮, 崔亚奇, 熊伟, 熊振宇, 顾祥岐. 生成式中断航迹接续关联方法[J]. 系统工程与电子技术, 2022, 44(5): 1543-1552.
[6]	曹鹏宇, 杨承志, 石礼盟, 吴宏超. 基于PSO-DBSCAN和SCGAN的未知雷达信号处理方法[J]. 系统工程与电子技术, 2022, 44(4): 1158-1165.
[7]	陈冬, 句彦伟. 基于语义分割实现的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(4): 1195-1201.
[8]	方伟, 王玉, 闫文君, 林冲. 基于神经网络的符号化飞行动作识别[J]. 系统工程与电子技术, 2022, 44(3): 737-745.
[9]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3): 802-807.
[10]	刘恒燕, 张立民, 闫文君, 钟兆根, 凌青, 梁晓军. 基于WBP-CNN算法的LDPC译码[J]. 系统工程与电子技术, 2022, 44(3): 1030-1035.
[11]	张玺, 金正猛, 姜亚琴. 融合深度图像先验的全变差图像着色算法[J]. 系统工程与电子技术, 2022, 44(2): 385-393.
[12]	金涛, 王晓峰, 田润澜, 张歆东. 基于改进1DCNN+TCN的雷达辐射源快速识别方法[J]. 系统工程与电子技术, 2022, 44(2): 463-469.
[13]	吕勤哲, 全英汇, 沙明辉, 董淑仙, 邢孟道. 基于集成深度学习的有源干扰智能分类[J]. 系统工程与电子技术, 2022, 44(12): 3595-3602.
[14]	高涌荇, 王旭东, 汪玲, 朱岱寅, 郭军, 孟凡旺. 基于RCNN的双极化气象雷达天气信号检测[J]. 系统工程与电子技术, 2022, 44(11): 3380-3387.
[15]	李永刚, 朱卫纲, 黄琼男, 李云涛, 何永华. 复杂背景下SAR图像近岸舰船目标检测[J]. 系统工程与电子技术, 2022, 44(10): 3096-3103.

基于生成对抗与卷积神经网络的调制识别方法

Modulation recognition method based on generative adversarial andconvolutional neural network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价