EUVIMEDEUVIMED entdecken
Crossref

Channel Knowledge Map Construction With Radio Propagation Graph Representation Learning

Shimon Takagi, Koya Sato, Katsuya Suto

IEEE Internet of Things Journal · 01.06.2026 · 13 (11) · 24649-24664

DOI: 10.1109/jiot.2026.3672928 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.06.2026. Verfasst von Shimon Takagi und 2 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science (JSPS) KAKENHI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article presents a novel framework for constructing channel knowledge maps (CKMs) with high accuracy and computational efficiency. The proposed radio propagation graph representation learning (RPGRL) framework integrates physics-based modeling and data-driven learning through end-to-end optimization using only measured received power data. In RPGRL, both propagation probability and received power estimations are jointly optimized without requiring explicit path supervision, enabling adaptive graph-based representations that account for uncertainties in reflections caused by surface scattering and angular errors introduced by 3-D building map quantization. Experimental evaluations using real-world signal measurement data collected in an urban environment demonstrate that RPGRL significantly improves received power estimation accuracy while reducing computation time by more than 70% compared to conventional ray tracing (RT). Furthermore, it outperforms existing deep learning-based methods, such as RadioUNet, by leveraging path-aware estimation grounded in radio propagation physics. These results highlight RPGRL as a promising and practical approach for environment-aware communication and intelligent wireless network design toward sixth-generation (6G).

Förderung

  • Japan Society for the Promotion of Science (JSPS) KAKENHI

Zitieren

APA

Takagi, S., Sato, K., & Suto, K. (2026). Channel Knowledge Map Construction With Radio Propagation Graph Representation Learning. IEEE Internet of Things Journal, 13(11), 24649-24664. https://doi.org/10.1109/jiot.2026.3672928

Vancouver

Takagi S, Sato K, Suto K. Channel Knowledge Map Construction With Radio Propagation Graph Representation Learning. IEEE Internet of Things Journal. 2026;13(11):24649-24664. doi:10.1109/jiot.2026.3672928

BibTeX
@article{Takagi2026,
  author = {Takagi, Shimon and Sato, Koya and Suto, Katsuya},
  title = {Channel Knowledge Map Construction With Radio Propagation Graph Representation Learning},
  journal = {IEEE Internet of Things Journal},
  year = {2026},
  volume = {13},
  number = {11},
  pages = {24649--24664},
  doi = {10.1109/jiot.2026.3672928}
}
Kostenlos starten →