江苏科技大学海洋学院;中国人民解放军95829部队;
针对自动调制识别(Automatic Modulation Recognition, AMR)技术在复杂电磁环境下部分调制信号易混淆、识别准确率较低的问题，提出一种基于多注意力残差网络和门控循环单元(Gated Recurrent Unit, GRU)的AMR模型。通过数据预处理增强信号的相位特征信息，利用自注意力机制使模型有效提取信号的相位偏移特征；设计了由坐标注意力机制、多尺度卷积和通道注意力机制组成的融合注意力残差模块(Fusion Attention Residual Block, FARB),增强对信号空间特征的关注度，有效提取信号的空间特征；使用GRU提取信号的时序特征，通过结合信号的时空特征，提高调制识别精度；通过全连接层进行调制信号分类。仿真结果表明，在RadioML2016.10b数据集上，提出的模型识别准确率有较大提升，且模型参数量少于大多现有模型。此外，对于其他模型易混淆的16-QAM和64-QAM两种信号，所提模型具有较好的识别能力。
| 354 | 0 | 75 |
| 下载次数 | 被引频次 | 阅读次数 |
[1] 何继爱，张文琪.通信信号调制识别技术及其发展[J].高技术通讯，2016,26(2):157-165.
[2] CUTNO P,CHENG C H.A Software-defined Radio Based Automatic Modulation Classifier[C]//2017 Wireless Telecommunications Symposium(WTS).Chicago:IEEE,2017:1-6.
[3] 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.
[4] 吴斌，袁亚博，汪勃.基于记忆因子的连续相位调制信号最大似然调制识别[J].电子与信息学报，2016,38(10):2546-2552.
[5] 曾旭，慕晓冬，易昭湘，等.基于改进的瞬时信息量数字调制识别算法[J].无线电工程，2016,46(12):21-25.
[6] O'SHEA T J,CORGAN J,CLANCY T C.Convolutional Radio Modulation Recognition Networks[C]∥Proceedings of International Conference on Engineering Applications of Neural Network.Aberdeen:Springer,2016:213-226.
[7] RAJENDRAN S,MEERT W,POLLIN S,et al.Deep Learning Models for Wireless Signal Classification with Distributed Low-cost Spectrum Sensors[J].IEEE Transactions on Cognitive Communications and Networking,2018,4(3):433-445.
[8] 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.
[9] NJOKU J N,MOROCHO-CAYAMCELA M E,LIM W.CGDNet:Efficient Hybrid Deep Learning Model for Robust Automatic Modulation Recognition[J].IEEE Networking Letters,2021,3(2):47-51.
[10] SUN S Q,WANG Y Y.A Novel Deep Learning Automatic Modulation Classifier with Fusion of Multichannel Information Using GRU[J].EURASIP Journal on Wireless Communications and Networking,2023,2023(1):66.
[11] NISAR M Z,IBRAHIM M S,USMAN M,et al.A Lightweight Deep Learning Model for Automatic Modulation Classification Using Residual Learning and Squeeze-Excitation Blocks[J].Applied Sciences,2023,13(8):5145.
[12] 廖星，高勇.利用信号变换域的深度学习调制识别算法[J].无线电工程，2022,52(9):1574-1579.
[13] ZHANG R,YIN Z D,WU Z L,et al.A Novel Automatic Modulation Classification Method Using Attention Mechanism and Hybrid Parallel Neural Network[J].Applied Sciences,2021,11(3):1327.
[14] ZHANG R Y,CHANG S,WEI Z Q,et al.Modulation Classification of Active Attacks in Internet of Things:Lightweight MCBLDN with Spatial Transformer Network[J].IEEE Internet of Things Journal,2022,9(19):19132-19146.
[15] KIM S H,MOON C B,KIM J W,et al.A Hybrid Deep Learning Model for Automatic Modulation Classification[J].IEEE Wireless Communications Letters,2022,11(2):313-317.
[16] HU J,SHEN L,SUN G,et al.Squeeze-and-Excitation Networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:7132-7141.
[17] HOU Q B,ZHOU D Q,FENG J S.Coordinate Attention for Efficient Mobile Network Design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville:IEEE,2021:13713-13722.
[18] ZHANG F X,LUO C B,XU J L,et al.An Efficient Deep Learning Model for Automatic Modulation Recognition Based on Parameter Estimation and Transformation[J].IEEE Communications Letters,2021,25(10):3287-3290.
[19] WEST N E,O'SHEA T.Deep Architectures for Modulation Recognition[C]//2017 IEEE International Symposium on Dynamic Spectrum Access Networks(DySPAN).Baltimore:IEEE,2017:1-6.
[20] TEKBIYIK K,EKTI A R,G?R?■N A,et al.Robust and Fast Automatic Modulation Classification with CNN Under Multipath Fading Channels[C]//2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring).Antwerp:IEEE,2020:1-6.
基本信息:
DOI：
中图分类号:TN911.3;TP18
引用信息:
[1]李鸣皓,解志斌,颜培玉等.基于多注意力残差网络和GRU的自动调制识别算法[J].无线电工程,2025,55(01):36-44.
基金信息:
高端外国专家引进计划(G2023014110); 国家自然科学基金(62276117)~~