重庆理工大学电气与电子工程学院;
针对低信噪比下神经网络难以提取数字信号空间特征的问题，提出一种基于坐标注意力机制的数字信号识别方案。将8种数字信号进行正交调制，根据其幅度、相位信息序列进行预编码处理，在不同的训练步长下，提取分析数字信号幅度和相位的关键特征，选取合适的神经网络超参数，使网络达到拟合面。坐标注意力机制将数字信号特征进行2个一维特征编码，分别沿纵向和横向捕获幅度和相位的远程依赖关系；将生成的数字信号特征编码为一对方向感知和位置敏感的权重系数，进行数字信号特征的重标定。仿真结果表明，8种数字信号下，调制方式识别率高于95%时，卷积神经网络(Convolutional Neural Network, CNN)中坐标注意力机制信噪比增益约为4 dB,残差神经网络中坐标注意力机制信噪比增益约为8 dB。坐标注意力机制取得了较高的识别率以及更好的信噪比增益，与通道注意力机制、空间注意力机制相比更适用于数字信号解调的应用。
| 187 | 0 | 27 |
| 下载次数 | 被引频次 | 阅读次数 |
[1] MENG F,CHEN P,WU L N,et al.Automatic Modulation Classification:A Deep Learning Enabled Approach[J].IEEE Transactions on Vehicular Technology,2018,67(11):10760-10772.
[2] 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,2018,6:18484-18501.
[3] 李峰.基于卷积神经网络的调制信号识别算法研究[D].南京：南京信息工程大学，2021.
[4] O’SHEA T J,CORGAN J,CLANCY T C.Convolutional Radio Modulation Recognition Networks[C]//Engineering Applications of Neural Networks.Aberdeen:Springer,2016:213-226.
[5] 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.
[6] LIU X Y,YANG D Y,GAMAL A E.Deep Neural Network Architectures for Modulation Classification[C]//2017 51st Asilomar Conference on Signals,Systems,and Computers.Pacific Grove:IEEE,2017:915-919.
[7] WANG Y,LIU M,YANG J,et al.Data-driven Deep Learning for Automatic Modulation Recognition in Cognitive Radios[J].IEEE Transactions on Vehicular Technology,2019,68(4):4074-4077.
[8] KARRA K,KUZDEBA S,PETERSEN J.Modulation Reco-gnition Using Hierarchical Deep Neural Networks[C]//2017 IEEE International Symposium on Dynamic Spectrum Access Networks (Dyspan).Baltimore:IEEE,2017:1-3.
[9] KHAN F N,LU C,LAU A P T.Joint Modulation Format/Bit-rate Classification and Signal-to-Noise Ratio Estimation in Multipath Fading Channels Using Deep Machine Learning[J].Electronics Letters,2016,52(14):1272-1274.
[10] ZHANG Z F,WANG C,GAN C Q,et al.Automatic Modulation Classification Using Convolutional Neural Network with Features Fusion of SPWVD and BJD[J].IEEE Transactions on Signal and Information Processing over Networks,2019,5(3):469-478.
[11] HOU Q B,ZHOU D Q,FENG J S.Coordinate Attention for Efficient Mobile Network Design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville:IEEE,2021:13708-13717.
[12] MANDT S,HOFFMAN M D,BLEI D M.Stochastic Gradient Descent as Approximate Bayesian Inference[EB/OL].(2017-04-13)[2023-07-01].https://arxiv.org/pdf/1704.04289v1.pdf.
[13] SHELHAMER E,LONG J,DARRELL T.Fully Comvolutional Network for Semantic Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[14] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet Classification with Deep Convolutional Neural Networks[J].Communications of the ACM,2017,60(6):84-90.
[15] ZHAO H S,SHI J P,QI X J,et al.Pyramid Scene Parsing Network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017:6230-6239.
[16] HOU Q B,ZHANG L,CHENG M M,et al.Strip Pooling:Rethinking Spatial Pooling for Scene Parsing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle:IEEE,2020:4003-4012.
[17] HU J,SHEN L,SUN G.Squeeze-and-Excitation Networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:7132-7141.
[18] NAIR V,HINTON G E.Rectified Linear Units Improve Restricted Boltzmann Machines[C]//Proceedings of the 27th International Conference on Machine Learning.Haifa:ACM,2010:807-814.
[19] 陶志勇，闫明豪，刘影，等.基于AG-CNN的轻量级调制识别方法[J].电子测量与仪器学报，2022,36(4):241-249.
[20] 董聪，张传武，高勇.基于残差神经网络的通信混合信号识别[J].无线电工程，2020,50(9):727-731.
基本信息:
DOI：
中图分类号:TN911.3
引用信息:
[1]张兢,兰思源,曹阳等.数字信号调制识别下坐标注意力机制方案研究[J].无线电工程,2024,54(06):1398-1406.
基金信息:
重庆市教委科学技术项目(KJQN201901125); 重庆市基础与前沿研究计划项目(cstc2019jcy-msxmX0233)~~