EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SSA-A-BiGCRNN: An Attention-Based Spectrum Prediction Method for Spatio-Temporal Feature Synergy

Yueshun He, Hao Song, Ping Du, Linlin He, Xiaoyu Cao, Yunzhe Liu, Weiqian Song

Telecom · 28.05.2026 · 7 (3) · 61

DOI: 10.3390/telecom7030061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Telecom, online erschienen am 28.05.2026. Verfasst von Yueshun He und 6 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: East China University of Technology, Jiangxi Provincial 03 Special Zone and 5G Project, Center for Science and Technology Development, Ministry of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spectrum prediction is essential for implementing dynamic spectrum management and mitigating spectrum congestion. However, spectrum data in real electromagnetic environments exhibit high non-stationarity, multi-scale features, and complex non-Euclidean spatio-temporal coupling characteristics, which limit the prediction accuracy of existing models. To address these issues, this paper proposes an attention-based spectrum prediction method for spatio-temporal feature synergy (SSA-A-BiGCRNN). First, Singular Spectrum Analysis (SSA) is introduced to decompose and reconstruct the non-stationary spectrum signals, filtering out high-frequency burst noise and extracting core evolutionary trends. Second, a spatial topology graph among multiple frequency bands is constructed based on the Spearman rank correlation coefficient. A Bidirectional Graph Convolutional Recurrent Neural Network is then designed to simultaneously capture the spatial dependencies between frequency bands and the bidirectional evolutionary patterns in the time dimension. Finally, an attention mechanism is incorporated during the feature fusion stage to evaluate and focus on critical spatio-temporal information, further enhancing global prediction accuracy. Experimental results based on a real electromagnetic monitoring dataset demonstrate that the proposed model achieves an accuracy of 96.82%, a coefficient of determination (R2) of 0.9966, a Root Mean Square Error (RMSE) of 0.5597, and a Mean Absolute Error (MAE) of 0.4031, significantly outperforming existing models.

Förderung

  • East China University of Technology
  • Jiangxi Provincial 03 Special Zone and 5G Project
  • Center for Science and Technology Development, Ministry of Education

Zitieren

APA

He, Y., Song, H., Du, P., He, L., Cao, X., Liu, Y., & Song, W. (2026). SSA-A-BiGCRNN: An Attention-Based Spectrum Prediction Method for Spatio-Temporal Feature Synergy. Telecom, 7(3), 61. https://doi.org/10.3390/telecom7030061

Vancouver

He Y, Song H, Du P, He L, Cao X, Liu Y, et al. SSA-A-BiGCRNN: An Attention-Based Spectrum Prediction Method for Spatio-Temporal Feature Synergy. Telecom. 2026;7(3):61. doi:10.3390/telecom7030061

BibTeX
@article{He2026,
  author = {He, Yueshun and Song, Hao and Du, Ping and He, Linlin and Cao, Xiaoyu and Liu, Yunzhe and Song, Weiqian},
  title = {SSA-A-BiGCRNN: An Attention-Based Spectrum Prediction Method for Spatio-Temporal Feature Synergy},
  journal = {Telecom},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {61},
  doi = {10.3390/telecom7030061}
}
Kostenlos starten →