基于时序深度残差收缩网络的混叠信号调制识别方法

刘京华; 魏祥麟; 范建华; 胡永扬; 王晓波; 于兵

doi:10.11959/j.issn.1000-0801.2024207

您当前的位置：

首页 >

文章列表页 >

基于时序深度残差收缩网络的混叠信号调制识别方法

研究与开发 | 更新时间：2024-12-02

- 基于时序深度残差收缩网络的混叠信号调制识别方法
- Mixed signal modulation recognition method based on temporal depth residual shrinkage network
- 电信科学 2024年40卷第10期页码：27-38
- 作者机构：
  
  1.南京信息工程大学电子与信息工程学院，江苏南京 210044
  2.国防科技大学第六十三研究所，江苏南京 210007
- 作者简介：
  
  [ "刘京华（1997- ），男，南京信息工程大学硕士生，主要研究方向为深度学习和移动计算。" ]
  魏祥麟，wei_xianglin@163.com
  范建华（1971- ），男，博士，现就职于国防科技大学第六十三研究所，主要研究方向为软件无线电和频谱智能计算。
  胡永扬（1977- ），男，博士，国防科技大学第六十三研究所高级工程师，主要研究方向为软件无线电和频谱智能计算。
  王晓波（1982- ），男，博士，国防科技大学第六十三研究所工程师，主要研究方向为移动智能计算。
  于兵（1981- ），男，博士，南京信息工程大学副教授，主要研究方向为微波技术、射频感知和电磁超材料。
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2024207
  中图分类号： TN929.5
- 收稿日期：2024-04-24，
  
  修回日期：2024-06-14，
  
  纸质出版日期：2024-10-20
- 稿件说明：
移动端阅览
刘京华,魏祥麟,范建华等.基于时序深度残差收缩网络的混叠信号调制识别方法[J].电信科学,2024,40(10):27-38.

LIU Jinghua,WEI Xianglin,FAN Jianhua,et al.Mixed signal modulation recognition method based on temporal depth residual shrinkage network[J].Telecommunications Science,2024,40(10):27-38.
刘京华,魏祥麟,范建华等.基于时序深度残差收缩网络的混叠信号调制识别方法[J].电信科学,2024,40(10):27-38. DOI： 10.11959/j.issn.1000-0801.2024207.

LIU Jinghua,WEI Xianglin,FAN Jianhua,et al.Mixed signal modulation recognition method based on temporal depth residual shrinkage network[J].Telecommunications Science,2024,40(10):27-38. DOI： 10.11959/j.issn.1000-0801.2024207.

摘要

基于深度学习进行信号自动调制识别在分类精度、可迁移性等方面普遍优于传统方法，引起广泛关注。但是，当前方法多数针对单信号样本进行识别，无法适用于混叠信号识别场景。针对该问题，对混叠信号调制识别方法进行了研究，结合长短期记忆（long short term memory，LSTM）网络和深度残差收缩网络（deep residual shrinkage network，DRSN），设计了时序深度残差收缩网络模型，其中包含残差模块、收缩模块和LSTM模块。残差模块和收缩模块负责提取混叠信号中的显著信息并自适应生成决策阈值，LSTM模块用于提取混叠信号中的时序隐含特征。三者结合可以有效提高混叠信号的识别精度。公开和实测数据集测试结果表明，所提方法识别精度优于5种典型方法，在高信噪比下的平均识别分类准确率可以达到92.7%；21种混叠信号中有12种识别准确率接近100%。

Abstract

Deep learning-based automatic signal modulation recognition has generally outperformed traditional methods in terms of classification accuracy and transferability

garnering widespread attention. However

most existing methods are designed to recognize single signal samples and are not applicable to recognize scenarios involving overlapping signals. To address this limitation

a modulation recognition method for aliased signals was investigated and a temporal deep residual shrinkage network model by integrating LSTM and DRSN was developed. There were three key modules in the model: a residual module

a shrinkage module

and a LSTM module. Salient information from overlapping signals was extracted by the residual module and the shrinkage module and decision thresholds were adaptively generated

while the LSTM module is tasked with extracting temporal hidden signals within the aliased data. The recognition accuracy of aliased signals was enhanced by the combination of these modules significantly. Testing on both public and private datasets demonstrates that the proposed method outperforms five state-of-the-art approaches

achieving an average recognition and classification accuracy of 92.7% under high signal-to-noise ratio conditions. Notably

the recognition accuracy for 12 out of 21 types of aliased signals approaches 100%.

关键词

Keywords

references

LI X , DONG W , ZHANG S , et al . A survey on deep learning techniques in wireless signal recognition [J ] . Wireless Communications and Mobile Computing , 2019 : 1 - 12 .

ZHANG X , GE T , CHEN Z . Automatic modulation recognition of communication signals based on instantaneous statistical characteristics and SVM classifier [C ] // proceedings of the IEEE Asia-Pacific Conference on Antennas and Propagation(APCAP) . Piscataway : IEEE Press , 2018 : 344 - 346 .

杨洪娟 , 时统志 , 李博 , 等 . 基于联合特征参数的卫星单-混信号调制识别研究 [J ] . 电子与信息学报 , 2022 , 44 ( 10 ): 3499 - 3506 .

YANG H J , SHI T Z , LI B , et al . Research on satellite single-mixed signal modulation recognition based on joint feature parameters [J ] . Journal of Electronics & Information Technology , 2022 , 44 ( 10 ): 3499 - 3506 .

ZUO J , MIAO Y , ZHANG B , et al . Cyclostationary feature mode decomposition and its application in fault diagnosis of planetary gearboxes via built-in information [J ] . IEEE Sensors Journal , 2024 , 24 ( 2 ): 1129 - 1139 .

谢智东 , 谭信 , 袁昕旺 , 等 . 基于生成对抗数据增强支持向量机的小样本信号调制识别算法 [J ] . 电子与信息学报 , 2023 , 45 ( 6 ): 2071 - 2080 .

XIE Z D , TAN X , YUAN X W , et al . Small sample signal modulation recognition algorithm based on support vector machine enhanced by generative adversarial networks generated data [J ] . Journal of Electronics & Information Technology , 2023 , 45 ( 6 ): 2071 - 2080 .

XIE C , LI C , ZHANG C , et al . Hierarchical residual stochastic networks for time series recognition [J ] . Information Sciences , 2019 , 471 : 52 - 63 .

YAN H , WANG G , GAO F , et al . Dynamic convolutional neural network for wireless interference identification [J ] . IEEE Communications Letters , 2024 , 28 ( 1 ): 83 - 87 .

XU S , LIU L , ZHAO Z . DTFTCNet: radar modulation recognition with deep time-frequency transformation [J ] . IEEE Transactions on Cognitive Communications and Networking , 2023 , 9 ( 5 ): 1200 - 1210 .

曾泓然 , 高勇 . 一种采用预分类式神经网络的混叠信号识别方法 [J ] . 无线电工程 , 2023 , 53 ( 5 ): 1138 - 1144 .

ZENG H R , GAO Y . An overlapped signal recognition method used pre-classification neural network [J ] . Radio Engineering , 2023 , 53 ( 5 ): 1138 - 1144 .

HUANG S , YAO Y , WEI Z , et al . Automatic modulation classification of overlapped sources using multiple cumulants [J ] . IEEE Transactions on Vehicular Technology , 2017 , 66 ( 7 ): 6089 - 6101 .

DU Y , YANG X , ZHANG J , et al . Modulation recognition method of mixed signal based on intelligent analysis of cyclic spectrum section [J ] . Journal of System Simulation , 2023 , 35 ( 1 ): 146 - 157 .

XU W , GAN L , HUANG C . A robust deep learning-based beamforming design for RIS-Assisted multiuser MISO communications with practical constraints [J ] . IEEE Transactions on Cognitive Communications and Networking , 2022 , 8 ( 2 ): 694 - 706 .

MENG Y , YU L , WEI Y . Multi-label radar compound jamming signal recognition using complex-valued CNN with jamming class representation fusion [J ] . Remote Sensing , 2023 , 15 ( 21 ): 5180 .

YIN Z , ZHANG R , WU Z , et al . Co-channel multi-signal modulation classification based on convolution neural network [J ] . IEEE 89th Vehicular Technology Conference (VTC2019-Spring) , 2019 : 1 - 5 .

PAN Z , WANG S , ZHU M , et al . Automatic waveform recognition of overlapping LPI radar signals based on multi-instance multi-label learning [J ] . IEEE Signal Processing Letters , 2020 , 27 : 1275 - 1279 .

PAN Z , WANG S , LI Y . Residual attention-aided U-Net GAN and multi-instance multilabel classifier for automatic waveform recognition of overlapping LPI radar signals [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2022 , 58 ( 5 ): 4377 - 4395 .

PAN Z , WANG B , ZHANG R , et al . MIML-GAN: a GAN-based algorithm for multi-instance multi-label learning on overlapping signal waveform recognition [J ] . IEEE Transactions on Signal Processing , 2023 , 71 : 859 - 872 .

YANG W C , REN K , DU Y , et al . Modulation recognition method of mixed signals based on cyclic spectrum projection [J ] . Scientific Reports , 2023 , 13 : 21459 .

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 .

ZHOU S , WU Z , YIN Z , et al . Blind modulation classification for overlapped co-channel signals using capsule networks [J ] . IEEE Communications Letters , 2019 , 23 ( 10 ): 1849 - 1852 .

ZHANG R , ZHAO Y , YIN Z , et al . A reference signal-aided deep learning approach for overlapped signals automatic modulation classification [J ] . IEEE Communications Letters , 2023 , 27 ( 4 ): 1135 - 1139 .

LI J , QI L , LIN Y . Research on modulation identification of digital signals based on deep learning [C ] // proceedings of the IEEE International Conference on Electronic Information and Communication Technology (ICEICT) . Piscataway : IEEE Press , 2016 , 402 - 405 .

XU J , LIN Z . Modulation and classification of mixed signals based on deep learning [J ] . arXiv: 2205 . 09916 , 2022 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于深度学习的调制识别综述

GMTBLC：基于深度学习的双模态网络流量分类

基于改进YOLOv5的天线下倾角识别方法研究

日志信息驱动的计算机网络节点故障预测研究

信号增强网络驱动的调制识别