EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

A Three-Channel Improved SE Attention Mechanism Network Based on SVD for High-Order Signal Modulation Recognition

Xujia Zhou, Gangyi Tu, Xicheng Zhu, Di Zhao, Luyan Zhang

Electronics · 2025-05-30 · 14 (11) · 2233

DOI: 10.3390/electronics14112233 ↗

At a glance

Journal article in Electronics, published online on 2025-05-30. Written by Xujia Zhou and 4 co-authors. Cited 2 times so far (Crossref); 37 references. The full text is freely available (open access, CC BY 4.0). Funded by: The Startup Foundation for Introducing Talent of NUIST, Joint Fund of the Ministry of Education for Equipment Pre-Research (Innovative Teams), 173 Plan Project.

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

To address the issues of poor differentiation capability for high-order signals and low average recognition rates in existing communication modulation recognition techniques, this paper first performs denoising using an entropy-based dynamic Singular Value Decomposition (SVD) method and proposes a three-channel convolutional gated recurrent units (GRU) model combined with an improved SE attention mechanism for automatic modulation recognition.The model denoises in-phase/quadrature (I/Q) signals using the SVD method to enhance signal quality. By combining one-dimensional (1D) convolutional and two-dimensional (2D) convolutional, it employs a three-channel approach to extract spatial features and capture local correlations. GRU is utilized to capture temporal sequence features so as to enhance the perception of dynamic changes. Additionally, an improved SE block is introduced to optimize feature representation, adaptively adjust channel weights, and improve classification performance. Experiments on the RadioML2016.10a dataset show that the model has a maximum classification recognition rate of 92.54%. Compared with traditional CNN, ResNet, CLDNN, GRU2, DAE, and LSTM2, the average recognition accuracy is improved by 5.41% to 8.93%. At the same time, the model significantly enhances the differentiation capability between 16QAM and 64QAM, reducing the average confusion probability by 27.70% to 39.40%.

Funding

  • The Startup Foundation for Introducing Talent of NUIST
  • Joint Fund of the Ministry of Education for Equipment Pre-Research (Innovative Teams)
  • 173 Plan Project

Cite

APA

Zhou, X., Tu, G., Zhu, X., Zhao, D., & Zhang, L. (2025). A Three-Channel Improved SE Attention Mechanism Network Based on SVD for High-Order Signal Modulation Recognition. Electronics, 14(11), 2233. https://doi.org/10.3390/electronics14112233

Vancouver

Zhou X, Tu G, Zhu X, Zhao D, Zhang L. A Three-Channel Improved SE Attention Mechanism Network Based on SVD for High-Order Signal Modulation Recognition. Electronics. 2025;14(11):2233. doi:10.3390/electronics14112233

BibTeX
@article{Zhou2025,
  author = {Zhou, Xujia and Tu, Gangyi and Zhu, Xicheng and Zhao, Di and Zhang, Luyan},
  title = {A Three-Channel Improved SE Attention Mechanism Network Based on SVD for High-Order Signal Modulation Recognition},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {11},
  pages = {2233},
  doi = {10.3390/electronics14112233}
}
Start for free →