| 394 | 6 | 350 |
| 下载次数 | 被引频次 | 阅读次数 |
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。
Abstract：Considering the problems of Automatic Modulation Recognition(AMR) technology in complex electromagnetic environments where some modulated signals are easily confused and the recognition accuracy is low, an AMR model based on multi-attention residual networks and Gated Recurrent Unit(GRU) is proposed. Firstly, signal phase characteristics are enhanced through data preprocessing, enabling the model to effectively extract signal phase offset features using self-attention mechanisms. Secondly, a Fusion Attention Residual Block(FARB) is devised, incorporating coordinate attention mechanisms, multi-scale convolution, and channel attention mechanisms to improve focus on signal spatial features and facilitate their extraction. Subsequently, GRU is used to extract the temporal features of the signal, improving modulation recognition accuracy by combining the signal's spatiotemporal features. Finally, modulation signal classification is performed using fully connected layers. Simulation results show that the proposed model has a significant improvement in recognition accuracy on RadioML2016.10b dataset, and the number of model parameters is smaller than most existing models. Moreover, the proposed model has good recognition ability for 16-QAM and 64-QAM signals that are easily confused by other models.
[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:
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)~~
2024-06-13
2024-06-13
2024-06-13