基于多通道轻量化的自动调制识别网络

万进华; 尚俊娜; 张华娣

doi:10.11959/j.issn.1000-0801.2025012

您当前的位置：

首页 >

文章列表页 >

基于多通道轻量化的自动调制识别网络

研究与开发 | 更新时间：2025-03-11

- 基于多通道轻量化的自动调制识别网络
- An automatic modulation recognition network based on multi-channel lightweighting
- 电信科学 2025年41卷第2期页码：41-56
- 作者机构：
  
  1.杭州电子科技大学通信工程学院，浙江杭州 310018
  2.中国电子科技集团公司第三十六研究所，浙江嘉兴 314033
- 作者简介：
  
  [ "万进华（2001- ），男，杭州电子科技大学硕士生，主要研究方向为通信信号调制识别。" ]
  尚俊娜（1979- ），女，博士，杭州电子科技大学教授、硕士生导师，主要研究方向为卫星通信、导航与定位方面。 87071712@qq.com
  张华娣（1978- ），女，中国电子科技集团公司第36研究所正高级工程师、硕士生导师，主要研究方向为通信信号分析识别。
- 基金信息：
  
  浙江省教育厅一般科研项目(Y202455360);浙江省“十四五”第二批研究生省级教学改革项目(JGCG2024202)
- DOI：10.11959/j.issn.1000-0801.2025012
  中图分类号： TN92
- 收稿日期：2024-09-27，
  
  修回日期：2024-11-29，
  
  纸质出版日期：2025-02-20
- 稿件说明：
移动端阅览
万进华,尚俊娜,张华娣.基于多通道轻量化的自动调制识别网络[J].电信科学,2025,41(02):41-56.

WAN Jinhua,SHANG Junna,ZHANG Huadi.An automatic modulation recognition network based on multi-channel lightweighting[J].Telecommunications Science,2025,41(02):41-56.
万进华,尚俊娜,张华娣.基于多通道轻量化的自动调制识别网络[J].电信科学,2025,41(02):41-56. DOI： 10.11959/j.issn.1000-0801.2025012.

WAN Jinhua,SHANG Junna,ZHANG Huadi.An automatic modulation recognition network based on multi-channel lightweighting[J].Telecommunications Science,2025,41(02):41-56. DOI： 10.11959/j.issn.1000-0801.2025012.

摘要

自动调制识别技术在无线通信领域具有十分重要的作用。现有的自动调制识别模型在识别精度上表现出色，但大多数方法在参数量与模型性能之间难以实现理想的平衡。针对该问题，设计了一种多通道融合的轻量化调制识别（multi-channel lightweight modulation recognition，MCLMR）网络。MCLMR网络将幅度、相位、频率以及零中心归一化瞬时幅度的谱密度最大值作为输入。使用可分离卷积模块巧妙地组合4个输入，从而深入挖掘这4个输入的空间相关性。设计了基于时间衰落多头自注意力（multi-head self-attention，MHSA）机制结合门控循环单元（gated recurrent unit，GRU）的GRU-MHSA（gated recurrent unit-multi-head self-attention）模块进一步提取时间相关性。可分离卷积模块与GRU-MHSA模块的结合在空间维度与时间维度提取信号特征。在基准RML2016.10a数据集上的仿真结果表明，所提方法优于其他9种典型方法。在2~18 dB信噪比下平均识别精度达到92.39%，最高识别精度达到93.36%，这说明MCLMR不仅参数量少，计算复杂度低，在识别精度上也表现出色。

Abstract

Automatic modulation recognition technology plays an important role in the field of wireless communication. Existing automatic modulation recognition models perform well in recognition accuracy

but most methods have difficulty in achieving an ideal balance between the number of parameters and model performance. To solve this problem

a multi-channel lightweight modulation recognition (MCLMR) network was designed. The amplitude

phase

frequency

and maximum spectral density of the zero center normalized instantaneous amplitude were taken as inputs by the MCLMR network. A separable convolution module was used to cleverly combine four inputs to dig deeper into the spatial correlation of the four inputs. The gated recurrent unit-multi-head self-attention (GRU-MHSA) module multi-head self-attention (MHSA) based on time fading and gated recurrent unit (GRU). to further extract the temporal correlation. Signal features in spatial dimension and time dimension were extracted by the combination of separable convolution module and GRU-MHSA module. Simulation results on the benchmark dataset RML2016.10a show that the proposed method is superior to other 9 typical methods. At 2~18 dB signal-to-noise ratio

the average recognition accuracy reaches 92.39% and the highest recognition accuracy reaches 93.36%. This shows that MCLMR not only has a small number of parameters and low computational complexity

but also has excellent performance in recognition accuracy.

关键词

Keywords

references

DOBRE O A , ABDI A , BAR-NESS Y , et al . Survey of automatic modulation classification techniques: classical approaches and new trends [J ] . IET Communications , 2007 , 1 ( 2 ): 137 - 156 .

WEI W , MENDEL J M . Maximum-likelihood classification for digital amplitude-phase modulations [J ] . IEEE Transactions on Communications , 2000 , 48 ( 2 ): 189 - 193 .

SU W , XU J L , ZHOU M C . Real-time modulation classification based on maximum likelihood [J ] . IEEE Communications Letters , 2008 , 12 ( 11 ): 801 - 803 .

MARCHAND P , LE MARTRET C , LACOUME J L . Classification of linear modulations by a combination of different orders cyclic cumulants [C ] // Proceedings of the IEEE Signal Processing Workshop on Higher-Order Statistics . Piscataway : IEEE Press , 1997 : 47 - 51 .

GHASEMZADEH P , BANERJEE S , HEMPEL M , et al . Accuracy analysis of feature-based automatic modulation classification with blind modulation detection [C ] // Proceedings of the 2019 International Conference on Computing, Networking and Communications (ICNC) . Piscataway : IEEE Press , 2019 : 1000 - 1004 .

O’SHEA T J , CORGAN J , CLANCY T C . Convolutional radio modulation recognition networks [C ] // Proceedings of the JAYNE C , ILIADIS L, eds. Communications in Computer and Information Science . Cham : Springer International Publishing , 2016 : 213 - 226 .

WEST N E , O’SHEA T . Deep architectures for modulation recognition [C ] // Proceedings of the 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN) . Piscataway : IEEE Press , 2017 : 1 - 6 .

CHEN Y F , SHAO W , LIU J , et al . Automatic modulation classification scheme based on LSTM with random erasing and attention mechanism [J ] . IEEE Access , 2020 , 8 : 154290 - 154300 .

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 .

LIU K , XIANG X , LIANG Y , et al . Automatic modulation recognition through wireless sensor networks in aeronautical wireless channel [J ] . IEEE Sensors Journal , 2021 , 21 ( 20 ): 23125 - 23132 .

WU Y L , LI X J , FANG J . A deep learning approach for modulation recognition via exploiting temporal correlations [C ] // Proceedings of the 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) . Piscataway : IEEE Press , 2018 : 1 - 5 .

PERENDA E , RAJENDRAN S , POLLIN S . Automatic modulation classification using parallel fusion of convolutional neural networks [J ] . BalkanCom'19 , 2019 .

ZHANG Z F , LUO H , WANG C , et al . Automatic modulation classification using CNN-LSTM based dual-stream structure [J ] . IEEE Transactions on Vehicular Technology , 2020 , 69 ( 11 ): 13521 - 13531 .

HUYNH-THE T , HUA C H , PHAM Q V , et al . MCNet: an efficient CNN architecture for robust automatic modulation classification [J ] . IEEE Communications Letters , 2020 , 24 ( 4 ): 811 - 815 .

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 .

XU J L , LUO C B , PARR G , et al . A spatiotemporal multi-channel learning framework for automatic modulation recognition [J ] . IEEE Wireless Communications Letters , 2020 , 9 ( 10 ): 1629 - 1632 .

WANG X , LIU D J , ZHANG Y H , et al . A spatiotemporal multi-stream learning framework based on attention mechanism for automatic modulation recognition [J ] . Digital Signal Processing , 2022 ( 130 ): 103703 .

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 .

LI L , ZHU Y X , ZHU Z G . Automatic modulation classification using ResNet-GRU with deep feature fusion [J ] . IEEE Transactions on Instrumentation and Measurement , 2023 ( 72 ): 2519710 .

ELSAGHEER M M , RAMZY S M . A hybrid model for automatic modulation classification based on residual neural networks and long short term memory [J ] . Alexandria Engineering Journal , 2023 ( 67 ): 117 - 128 .

LIN W S , HOU D B , HUANG J S , et al . Transfer learning for automatic modulation recognition using a few modulated signal samples [J ] . IEEE Transactions on Vehicular Technology , 2023 , 72 ( 9 ): 12391 - 12395 .

PAN Z S , WANG S F , LI Y J . Residual attention-aided U-net GAN and multi-instance multilabel classifier for automatic waveform recognition of overlapping LPI radar signals [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2022 , 58 ( 5 ): 4377 - 4395 .

NANDI A K , AZZOUZ E E . Algorithms for automatic modulation recognition of communication signals [J ] . IEEE Transactions on Communications , 1998 , 46 ( 4 ): 431 - 436 .

HONG D H , ZHANG Z L , XU X D . Automatic modulation classification using recurrent neural networks [C ] // Proceedings of the 2017 3rd IEEE International Conference on Computer and Communications (ICCC) . Piscataway : IEEE Press , 2017 : 695 - 700 .

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 .

LIU X Y , YANG D Y , EL GAMAL A . Deep neural network architectures for modulation classification [C ] // Proceedings of the 2017 51st Asilomar Conference on Signals, Systems, and Computers . Piscataway : IEEE Press , 2017 : 915 - 919 .

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 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于时序深度残差收缩网络的混叠信号调制识别方法

信号增强网络驱动的调制识别

基于DropBlock双模态混合神经网络的无线通信调制识别

基于深度学习的调制识别综述