基于CBAM-GRU的通信信号自动调制识别

Automatic Modulation and Recognition of Communication Signals Based on CBAM-GRU

杨宵 ¹姚爱琴 ¹孙运强 ¹石喜玲 ¹张婉婷¹

扫码查看

作者信息

1. 中北大学信息与通信学院太原 030051
折叠

摘要

本文研究了一种基于卷积注意力机制模块(CBAM)与门控循环单元网络(GRU)结合的CBAM-GRU分类模型,用于非合作通信系统中的自动调制识别技术.将信号预处理后的时域幅度值、相位值以及I/Q值合并,转换为输入采样值矩阵,进入网络进行信号分类识别.使用无线电数据集RadioML2016.10a进行仿真实验,并将CBAM-GRU模型与卷积神经网络(CNN)、长短期记忆网络(LSTM)、GRU、卷积长短时深度神经网络(CLDNN)进行比较.实验结果表明:CBAM-GRU模型的分类识别率达到92.79%,相较于对比模型分别提高了8.52%、1.84%、1.75%、8.61%,比传统的CNN或LSTM模型,在处理信号时能够更有效地捕捉时空特征,从而提高识别精度.

Abstract

A CBAM-GRU classification model based on the combination of Convolutional Attention Mechanism Module(CBAM)and Gated Recurrent Unit(GRU)network is investigated for automatic modulation identification in non-cooperative com-munication systems.The pre-processed time-domain amplitude,phase and I/Q values of the signal are combined and converted into a matrix of input sample values,which are entered into the network for signal classification and identification.Simulations are con-ducted using the RadioML2016.10a radio dataset,and the CBAM-GRU model are compared with the Convolutional Neural Net-work(CNN),Long Short-Term Memory network(LSTM),GRU,and Convolutional Long Deep Neural Network(CLDNN).The re-sults indicates that the classification accuracy of the CBAM-GRU model reaches 92.79%,showing improvements of 8.52%,1.84%,1.75%,and 8.61%over the comparison models respectively.Compared to traditional CNN or LSTM models,the CBAM-GRU mod-el is more effective in capturing spatio-temporal features of sig-nals,thereby enhancing recognition accuracy.

关键词

自动调制识别/非合作通信系统/卷积注意力机制/门控循环单元网络

Key words

Automatic modulation recognition/Non-cooperative communication systems/Convolutional block attention mecha-nism/Gated recurrent unit network

引用本文复制引用

基金项目

山西省基础研究计划资助项目(20210302123062)

出版年

2024

遥测遥控

中国航天工业总公司第七0四研究所

遥测遥控

CSTPCD

影响因子：0.28

ISSN：

参考文献量6

段落导航