EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Dual-Branch Complex-Valued Neural Network for Automatic Modulation Classification of Communication Signals

Zhaojing Xu, Youchen Fan, Shengliang Fang, You Fu, Liu Yi

Sensors · 15.04.2025 · 25 (8) · 2489

DOI: 10.3390/s25082489 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.04.2025. Verfasst von Zhaojing Xu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Space Information, Space Engineering University, Beijing 101416, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Basic Research Projects of the Basic Strengthening Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Currently, deep learning has become a mainstream approach for automatic modulation classification (AMC) with its powerful feature extraction capability. Complex-valued neural networks (CVNNs) show unique advantages in the field of communication signal processing because of their ability to directly process complex data and obtain signal amplitude and phase information. However, existing models face deployment challenges due to excessive parameters and computational complexity. To address these limitations, a lightweight dual-branch complex-valued neural network (LDCVNN) is proposed. The framework uses dual pathways to separately capture features with phase information and complex-scaling-equivariant representations, adaptively fused via trainable weighted fusion. Spatial and channel reconstruction convolution (SCConv) is extended to complex domain and combined with complex-valued depthwise separable convolution block (CBlock) and complex-valued average pooling to eliminate feature redundancy and extract higher order features. Finally, efficient classification is realized through complex-valued fully connected layers and a complex-valued Softmax. The evaluations demonstrate that LDCVNN achieves the highest average accuracy on RML2016.10a with only 9.0 K parameters and without data augmentation, which reducing the number of parameters by 99.33% compared to CDSN and by 97.25% compared to CSDNN. Additionally, LDCVNN achieves a better balance between efficiency and performance across other datasets.

Schlagwörter

Stichwörter der Autor:innen

Riemannian manifoldautomatic modulation classification (AMC)complex-valued neural networks (CVNNs)deep learning

Autor:innen und Institutionen

  • School of Space Information, Space Engineering University, Beijing 101416, China.
  • Graduate School, Space Engineering University, Beijing 101416, China.

Förderung

  • Key Basic Research Projects of the Basic Strengthening Program

Zitieren

APA

Xu, Z., Fan, Y., Fang, S., Fu, Y., & Yi, L. (2025). A Lightweight Dual-Branch Complex-Valued Neural Network for Automatic Modulation Classification of Communication Signals. Sensors, 25(8), 2489. https://doi.org/10.3390/s25082489

Vancouver

Xu Z, Fan Y, Fang S, Fu Y, Yi L. A Lightweight Dual-Branch Complex-Valued Neural Network for Automatic Modulation Classification of Communication Signals. Sensors. 2025;25(8):2489. doi:10.3390/s25082489

BibTeX
@article{Xu2025,
  author = {Xu, Zhaojing and Fan, Youchen and Fang, Shengliang and Fu, You and Yi, Liu},
  title = {A Lightweight Dual-Branch Complex-Valued Neural Network for Automatic Modulation Classification of Communication Signals},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {8},
  pages = {2489},
  doi = {10.3390/s25082489}
}
Kostenlos starten →