EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RGF-Net: A Dual-Stream Spatiotemporal Fusion Network for Robust Automatic Modulation Recognition in Cognitive Radio

Fangning Shi, Yiheng Zhang, Yongkang Gong

Journal of Intelligent Computing and Networking · 06.05.2026 · 2 (1) · 70-76

DOI: 10.64509/jicn.21.95 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent Computing and Networking, online erschienen am 06.05.2026. Verfasst von Fangning Shi und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatic Modulation Recognition (AMR) is an enabling component of cognitive radio because it helps secondary users infer incumbent transmission formats under limited prior information. Existing single-stream deep networks often emphasize either spatial constellation structure or temporal evolution, which can reduce robustness under noisy channel conditions. This paper presents RGF-Net, a dual-stream framework that processes the same raw I/Q sequence with a ResNet branch and a GRU branch, then combines their class-posterior outputs through a learnable decision-fusion weight. The methodological contribution therefore lies in the parallel decomposition and end-to-end calibration of complementary spatial and temporal classifiers, rather than in proposing a new backbone block. Experiments on the synthetic RadioML2018.10a benchmark show that, among the compared models, RGF-Net achieves the highest accuracy across the evaluated SNR range and improves the 0 dB accuracy by 12.2 percentage points over the strongest single-branch baseline. These results indicate that the proposed fusion design is effective on this benchmark, while evaluation on additional real-world datasets remains necessary.

Zitieren

APA

Shi, F., Zhang, Y., & Gong, Y. (2026). RGF-Net: A Dual-Stream Spatiotemporal Fusion Network for Robust Automatic Modulation Recognition in Cognitive Radio. Journal of Intelligent Computing and Networking, 2(1), 70-76. https://doi.org/10.64509/jicn.21.95

Vancouver

Shi F, Zhang Y, Gong Y. RGF-Net: A Dual-Stream Spatiotemporal Fusion Network for Robust Automatic Modulation Recognition in Cognitive Radio. Journal of Intelligent Computing and Networking. 2026;2(1):70-76. doi:10.64509/jicn.21.95

BibTeX
@article{Shi2026,
  author = {Shi, Fangning and Zhang, Yiheng and Gong, Yongkang},
  title = {RGF-Net: A Dual-Stream Spatiotemporal Fusion Network for Robust Automatic Modulation Recognition in Cognitive Radio},
  journal = {Journal of Intelligent Computing and Networking},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {70--76},
  doi = {10.64509/jicn.21.95}
}
Kostenlos starten →