EUVIMEDEUVIMED entdecken
Crossref

PhySNet: Physics-Inspired Spectral–Spatial Decoupled Attention for Radio Map Estimation

Chunyan Qiu, Kangjun Liu, Songfeng Zhong, Yu Zhang, Xinhuai Wang, Ke Chen

IEEE Communications Letters · 2026 · 30 · 2426-2430

DOI: 10.1109/lcomm.2026.3705413 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Chunyan Qiu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben. Gefördert von: Major Key Project of Pengcheng Laboratory, Key R&D Program Project of Shaanxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Radio map estimation (RME) plays a critical role in spectrum management and network planning for 5G and beyond. In dense urban environments, however, the received signal strength (RSS) exhibits complex multi-scale characteristics, where smooth large-scale path loss coexists with sharp local variations caused by geometry-induced line-of-sight/non-line-of-sight (LOS/NLOS) transitions. Such heterogeneity poses a significant challenge for RME, especially under sparse sampling conditions. Existing interpolation- and learning-based methods often suffer from severe performance degradation, as they lack intrinsic physical propagation priors to effectively model these heterogeneous patterns. To address this challenge, we propose PhySNet, a physics-inspired framework that explicitly disentangles large-scale trends and local variations through FFT-based spectral decomposition. The resulting decoupled components are then utilized as physics-guided queries in a novel Spectral Cross-Window Attention (SCWA) mechanism, enabling efficient spatial feature aggregation. Subsequently, a spatially aware fusion network further refines the aggregated features by incorporating local environmental semantics. Experimental results on ray-tracing-based urban simulation datasets demonstrate that PhySNet consistently outperforms state-of-the-art methods in terms of RMSE and spatial consistency, offering a robust and scalable solution for rapid radio map construction in complex electromagnetic environments.

Förderung

  • Major Key Project of Pengcheng Laboratory
  • Key R&D Program Project of Shaanxi Province

Zitieren

APA

Qiu, C., Liu, K., Zhong, S., Zhang, Y., Wang, X., & Chen, K. (2026). PhySNet: Physics-Inspired Spectral–Spatial Decoupled Attention for Radio Map Estimation. IEEE Communications Letters, 30, 2426-2430. https://doi.org/10.1109/lcomm.2026.3705413

Vancouver

Qiu C, Liu K, Zhong S, Zhang Y, Wang X, Chen K. PhySNet: Physics-Inspired Spectral–Spatial Decoupled Attention for Radio Map Estimation. IEEE Communications Letters. 2026;30:2426-2430. doi:10.1109/lcomm.2026.3705413

BibTeX
@article{Qiu2026,
  author = {Qiu, Chunyan and Liu, Kangjun and Zhong, Songfeng and Zhang, Yu and Wang, Xinhuai and Chen, Ke},
  title = {PhySNet: Physics-Inspired Spectral–Spatial Decoupled Attention for Radio Map Estimation},
  journal = {IEEE Communications Letters},
  year = {2026},
  volume = {30},
  pages = {2426--2430},
  doi = {10.1109/lcomm.2026.3705413}
}
Kostenlos starten →