基于多端卷积神经网络的调制识别方法

doi:10.11959/j.issn.1000-436x.2019206

通信学报 ›› 2019, Vol. 40 ›› Issue (11): 30-37.doi: 10.11959/j.issn.1000-436x.2019206

基于多端卷积神经网络的调制识别方法

查雄,彭华,秦鑫,李广,李天昀

信息工程大学信息系统工程学院，河南郑州 450001

修回日期:2019-08-20 出版日期:2019-11-25 发布日期:2019-12-06
作者简介:查雄（1995- ），男，江西九江人，信息工程大学博士生，主要研究方向为智能信号处理、软件无线电。|彭华（1973- ），男，江西萍乡人，博士，信息工程大学教授，主要研究方向为通信信号分析。|秦鑫（1994- ），女，重庆人，信息工程大学硕士生，主要研究方向为雷达信号处理。|李广（1996- ），男，湖南永州人，信息工程大学硕士生，主要研究方向为卫星通信技术。|李天昀（1979- ），男，江西萍乡人，博士，信息工程大学副教授，主要研究方向为软件无线电。
基金资助:
国家自然科学基金资助项目(61401511)

Modulation recognition method based on multi-inputs convolution neural network

Xiong ZHA,Hua PENG,Xin QIN,Guang LI,Tianyun LI

School of Information Systems Engineering,Information Engineering University,Zhengzhou 450001,China

Revised:2019-08-20 Online:2019-11-25 Published:2019-12-06
Supported by:
The National Natural Science Foundation of China(61401511)

摘要/Abstract

摘要：

为识别当前卫星通信系统所采用的主要调制方式，提出了一种基于多端卷积神经网络的通信信号调制识别算法。利用信号的先验信息以及对网络拓扑结构的认知，将信号时域波形转化为眼图和矢量图，作为信号的浅层特征表达，并由此设计了基于多端卷积神经网络的调制识别模型。通过训练所搭建的网络，对浅层特征进行深度提取和映射，最终完成了目标信号的调制识别。仿真实验表明，所提算法相对于传统调制识别算法以及目前基于波形和星座图的深度学习识别算法识别效果更好，当信噪比为5 dB时，识别性能可达95%。

关键词: 调制识别, 多端卷积神经网络, 眼图, 矢量图

Abstract:

In order to identify the main modulation modes adopted in current satellite communication systems,a signal modulation recognition algorithm based on multi-inputs convolution neural network was proposed.With the prior information of the signals and knowledge of the network topological structure,the time-domain signal waveforms were converted into eye diagrams and vector diagrams to represent the shallow features of the signals.Meanwhile,the modulation recognition model based on multi-inputs convolution neural network was designed.Through the training of the network,the shallow features were deeply extracted and mapped.Finally,the signal modulation recognition task was completed.The simulation results show that compared with the traditional algorithms and deep learning algorithms,the proposed method has a better anti-noise performance,and the overall recognition rate of this algorithm can reach 95% when the signal-to-noise ratio is 5 dB.

Key words: modulation recognition, multi-inputs convolution neural network, eye diagram, vector diagram

中图分类号:

TN911.7

查雄,彭华,秦鑫,李广,李天昀. 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.

Xiong ZHA,Hua PENG,Xin QIN,Guang LI,Tianyun LI. Modulation recognition method based on multi-inputs convolution neural network[J]. Journal on Communications, 2019, 40(11): 30-37.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

表1

不同算法时间复杂度对比"

$\frac{E_{b}}{N_{0}} / d B$					时间复杂度/ms
			样本生成过程					信号识别过程
	文献[4]	文献[5]	文献[8]	文献[9]	本文算法	文献[4]	文献[5]	文献[8]	文献[9]	本文算法
5	2.2	4.1	0	15.2	13.2	2.5	2.7	9.5	16.2	9.9
10	2.1	4.1	0	15.8	13.4	1.3	1.4	9.5	16.1	9.7

表1

图9

图10

图11

参考文献 14

[1]	廖灿辉, 涂世龙, 万坚 . 一种抗频偏的卫星幅相调制信号识别算法[J]. 电子与信息学报, 2014,36(2): 346-352.
	LIAO C H , TU S L , WAN J . An anti-frequency-offset algorithm for modulation recognition of satellite amplitude-phase modulated signals[J]. Journal of Electronics and Information Technology, 2014,36(2): 346-352.
[2]	刘明骞, 李兵兵, 曹超凤 ,等. 认知无线电中非高斯噪声下数字调制信号识别方法[J]. 通信学报, 2014,35(1): 82-88.
	LIU M Q , LI B B , CAO C F ,et al. Recognition method of digital modulation signals over non-Gaussian noise in cognitive radio[J]. Journal on Communications, 2014,35(1): 82-88.
[3]	NANDI A K , AZZOUZ E E . Algorithms for automatic modulation recognition of communication signals[J]. IEEE Transactions on Communications, 1998,46(4): 431-436.
[4]	SWAMI A , SADLER B M . Hierarchical digital modulation classification using cumulants[J]. IEEE Transactions on Communications, 2000,48(3): 416-429.
[5]	WEE T N , HI ASLAM M W , ZHU Z ,et al. Automatic modulation classification using combination of genetic programming and KNN[J]. IEEE Transactions on Wireless Communications, 2012,11(8): 2742-2750.
[6]	LI R , LI L , YANG S ,et al. Robust automated VHF modulation recognition based on deep convolutional neural networks[J]. IEEE Communications Letters, 2018,22(5): 946-949.
[7]	DENG L , YU D . Deep learning:methods and applications[J]. Foundations ＆ Trends in Signal Processing, 2014,7(3): 197-387.
[8]	KULIN M , KAZAZ T , MOERMAN I ,et al. End-to-end learning from spectrum data:a deep learning approach for wireless signal identification in spectrum monitoring applications[J]. IEEE Access, 2018,6(99): 18484-18501.
[9]	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 System, 2019 30(3): 718-727.
[10]	ETSI. Digital video broadcasting (DVB) user guidelines for the second generation system for broadcasting,interactive services,news gathering and other broadband satellite applications (DVB-S2)[S]. TR 102 376 v1.1.1. 2005.
[11]	KRIZHEYSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks[C]// International Conference on Neural Information Processing Systems. NIPC, 2014: 1097-1105.
[12]	IOFFE S , SZEGEDY C . Batch normalization:accelerating deep network training by reducing internal covariate shift[C]// International Conference on International Conference on Machine Learning. JMLR, 2015: 448-456.
[13]	HE K , ZHANG X , REN S ,et al. Deep residual learning for image recognition[C]// Computer Vision and Pattern Recognition. IEEE, 2016: 770-778.
[14]	MORELLI M , ANDREA A N D , MENGALI U . Feedforward ML-based timing estimation with PSK signals[J]. IEEE Communications Letters, 1997,1(3): 80-82.

基于多端卷积神经网络的调制识别方法

Modulation recognition method based on multi-inputs convolution neural network

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 14

相关文章 8

Metrics

推荐阅读 0

[1]	安泽亮, 张天骐, 马宝泽, 邓盼, 徐雨晴. 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.
[2]	李正权, 林媛, 李梦雅, 刘洋, 吴琼, 邢松. 基于判别式受限玻尔兹曼机的数字调制识别[J]. 通信学报, 2021, 42(2): 81-91.
[3]	戴江安, 栾声扬, 赵明龙, 张兆军, 邱天爽. 脉冲噪声下基于平滑循环相关熵谱的调制识别方法[J]. 通信学报, 2021, 42(12): 121-133.
[4]	张思成,林云,涂涯,ShiwenMao. 基于轻量级深度神经网络的电磁信号调制识别技术[J]. 通信学报, 2020, 41(11): 12-21.
[5]	李红光, 郭英, 眭萍, 齐子森. 基于时频能量谱纹理特征的跳频调制方式识别[J]. 通信学报, 2019, 40(10): 20-29.
[6]	刘明骞,李兵兵,曹超凤,李钊. 认知无线电中非高斯噪声下数字调制信号识别方法[J]. 通信学报, 2014, 35(1): 82-88.
[7]	胡国兵,徐立中,徐淑芳,吴珊珊,高燕. 基于能量聚焦效率检验的信号脉内调制识别[J]. 通信学报, 2013, 34(6): 136-145.
[8]	胡国兵1,2，徐立中1，徐淑芳1，吴珊珊2，高燕2. 基于能量聚焦效率检验的信号脉内调制识别[J]. 通信学报, 2013, 34(6): 17-145.