EUVIMEDEUVIMED entdecken
Crossref

A Convolutional Neural Network Based Method for Accurate Computation of Scattered Fields From Reconfigurable Intelligent Surfaces

Yuanzhi Liu, Costas D. Sarris

IEEE Transactions on Antennas and Propagation · 2025-04 · 73 (4) · 2615-2627

DOI: 10.1109/tap.2025.3532123 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Antennas and Propagation, 2025-04. Verfasst von Yuanzhi Liu und 1 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: The University of Toronto-Huawei Wireless Research Innovation Lab.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The cell-to-cell coupling in a reconfigurable intelligent surface (RIS) is very different from a periodic structure, where coupling effects can be precisely evaluated via full-wave analysis with periodic boundary conditions (PBCs). We propose a novel method based on convolutional neural networks (CNNs), to predict the contribution of mutual coupling on the near-zone tangential electric field of every RIS unit cell that characterizes its scattering. Our CNN model incorporates an attention mechanism based on the squeeze-and-excitation (SE) block module, enhancing its capability to discern and quantify coupling effects, especially from neighboring cells surrounding the unit cell of interest. The predictions of the model enable the computation of RIS scattered fields, fully accounting for the aperiodic nature of an RIS. Comparisons to finite-element analysis confirm that our computed fields are accurate at any point and for any RIS configuration. Furthermore, our machine learning model generalizes well to different incident waves and RIS dimensions. Therefore, the proposed method is a valuable tool for various practical applications, such as synthesizing RIS scattered field patterns and evaluating the performance of RIS-enabled channels.

Förderung

  • The University of Toronto-Huawei Wireless Research Innovation Lab

Zitieren

APA

Liu, Y., & Sarris, C. D. (2025). A Convolutional Neural Network Based Method for Accurate Computation of Scattered Fields From Reconfigurable Intelligent Surfaces. IEEE Transactions on Antennas and Propagation, 73(4), 2615-2627. https://doi.org/10.1109/tap.2025.3532123

Vancouver

Liu Y, Sarris CD. A Convolutional Neural Network Based Method for Accurate Computation of Scattered Fields From Reconfigurable Intelligent Surfaces. IEEE Transactions on Antennas and Propagation. 2025;73(4):2615-2627. doi:10.1109/tap.2025.3532123

BibTeX
@article{Liu2025,
  author = {Liu, Yuanzhi and Sarris, Costas D.},
  title = {A Convolutional Neural Network Based Method for Accurate Computation of Scattered Fields From Reconfigurable Intelligent Surfaces},
  journal = {IEEE Transactions on Antennas and Propagation},
  year = {2025},
  volume = {73},
  number = {4},
  pages = {2615--2627},
  doi = {10.1109/tap.2025.3532123}
}
Kostenlos starten →