| 196 | 0 | 87 |
| 下载次数 | 被引频次 | 阅读次数 |
针对自动调制识别(Automatic Modulation Recognition, AMR)方法在低信噪比(Signal to Noise Ratio, SNR)条件下识别准确率较低的问题，提出了一种基于卷积自适应降噪(Adaptive Noise Reduction, ANR)网络的AMR方法。相位变换用于降低相位偏移对调制识别的影响；卷积神经网络(Convolutional Neural Network, CNN)和门控循环单元(Gated Recurrent Unit, GRU)分别用于提取信号的空间特征和时间特征；在CNN后加入ANR模块，用于在不同SNR条件下对卷积特征进行自适应软阈值处理，提升网络鲁棒性。在基准数据集RML2016.10a上的仿真结果表明，提出的模型较其他网络模型，在SNR大于-8 dB时识别准确率得到了较好的提升。
Abstract：To deal with the problem of low recognition accuracy of Automatic Modulation Recognition(AMR) methods under low Signal to Noise Ratio(SNR) conditions, an AMR method is proposed based on convolutional Adaptive Noise Reduction(ANR). In this method, phase transformation is used to reduce the impact of phase shift on modulation recognition; Convolutional Neural Network(CNN) and Gated Recurrent Unit(GRU) are used to extract spatial and temporal features of signals, respectively; an ANR Module is added after CNN to perform adaptive soft thresholding on convolutional features under different SNR conditions to improve network robustness. The simulation results on the benchmark dataset RML2016.10a show that the proposed model achieves better recognition accuracy compared to other network models when the SNR is greater than-8 dB.
[1] XU J L,SU W,ZHOU M C.Likelihood-ratio Approaches to Automatic Modulation Classification[J].IEEE Transactions on Systems,Man,and Cybernetics,Part C (Applications and Reviews),2011,41(4):455-469.
[2] HAZZA A,SHOAIB M,ALSHEBEILI S A,et al.An Overview of Feature-based Methods for Digital Modulation Classification[C]//2013 1st International Conference on Communications,Signal Processing,and Their Applications (ICCSPA).Sharjah:IEEE,2013:1-6.
[3] CHAN Y,GADBOIS L,YANSOUNI P.Identification of the Modulation Type of a Signal[C]//ICASSP'85.IEEE International Conference on Acoustics,Speech,and Signal Processing.Tampa:IEEE,1985:838-841.
[4] HONG L,HO K C.Identification of Digital Modulation Types Using the Wavelet Transform[C]//MILCOM 1999.IEEE Military Communications.Conference Proceedings (Cat.No.99CH36341).Atlantic City:IEEE,1999:427-431.
[5] SWAMI A,SADLER B M.Hierarchical Digital Modulation Classification Using Cumulants[J].IEEE Transactions on Communications,2000,48(3):416-429.
[6] 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.
[7] 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.
[8] RAJENDRAN S,MEERT W,GIUSTINIANO D,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.
[9] 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.
[10] HERMAWAN A P,GINANJAR R R,KIM D S,et al.CNN-based Automatic Modulation Classification for Beyond 5G Communications[J].IEEE Communications Letters,2020,24(5):1038-1041.
[11] 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.
[12] ZHA Y P,WANG H J,SHEN Z X,et al.A Few-shot Modulation Recognition Method Based on Multi-modal Feature Fusion[J].IEEE Transactions on Vehicular Technology,2024,73(7):10823-10828.
[13] PENG S L,JIANG H Y,WANG H X,et al.Modulation Classification Based on Signal Constellation Diagrams and Deep Learning[J].IEEE Transactions on Neural Networks and Learning Systems,2019,30(3):718-727.
[14] LIN S G,ZENG Y,GONG Y.Learning of Time-frequency Attention Mechanism for Automatic Modulation Recognition[J].IEEE Wireless Communications Letters,2022,11(4):707-711.
[15] LIU F G,ZHANG Z W,ZHOU R L.Automatic Modulation Recognition Based on CNN and GRU[J].Tsinghua Science and Technology,2022,27(2):422-431.
[16] 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/OL].无线电工程，1-9[2024-06-15].http://kns.cnki.net/kcms/detail/13.1097.TN.20240613.1127.002.html.
[17] 庞伊琼，许华，蒋磊，等.基于混合注意力原型网络的调制识别算法[J].西北工业大学学报，2022,40(6):1375-1384.
[18] ZHAO M H,ZHONG S S,FU X Y,et al.Deep Residual Shrinkage Networks for Fault Diagnosis[J].IEEE Transactions on Industrial Informatics,2020,16(7):4681-4690.
[19] 竹杭杰，郭建新，张雨帅，等.基于DRSN的通信信号调制方式识别方法[J].无线电工程，2024,54(7):1643-1651.
[20] WEI T,LI Z,BI D X,et al.Adaptive Multi-dimensional Shrinkage Block for Automatic Modulation Recognition[J].IEEE Communications Letters,2023,27(11):2968-2972.
[21] WOO S,PARK J,LEE J Y,et al.CBAM:Convolutional Block Attention Module[EB/OL].(2018-07-17) [2024-06-12].https://arxiv.org/abs/1807.06521.
[22] DONOHO D L.De-noising by Soft-thresholding[J].IEEE Transactions on Information Theory,1995,41(3):613-627.
[23] ISOGAWA K,IDA T,SHIODERA T,et al.Deep Shrinkage Convolutional Neural Network for Adaptive Noise Reduction[J].IEEE Signal Processing Letters,2018,25(2):224-228.
基本信息:
DOI：
中图分类号:TN911.3;TP183
引用信息:
[1]陈昊,郭文普,康凯等.基于卷积自适应降噪网络的自动调制识别方法[J].无线电工程,2025,55(02):291-297.
基金信息: