EUVIMEDEUVIMED entdecken
Crossref

Field Reconstruction for High-Frequency Electromagnetic Exposure Assessment Based on Deep Learning

Miao Cao, Zicheng Liu, Bazargul Matkerim, Tongning Wu, Changyou Li, Yali Zong, Bo Qi

IEEE Transactions on Antennas and Propagation · 2026-07 · 74 (7) · 6954-6966

DOI: 10.1109/tap.2026.3681071 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Antennas and Propagation, 2026-07. Verfasst von Miao Cao und 6 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fifth-generation (5G) communication systems, operating in higher frequency bands from 3 to 300 GHz, provide unprecedented bandwidth to enable ultrahigh data rates and low-latency services. However, the use of millimeter-wave frequencies raises public health concerns regarding prolonged electromagnetic radiation (EMR) exposure. Above 6 GHz, the incident power density (IPD) is used instead of the specific absorption rate (SAR) for exposure assessment, owing to the shallow penetration depth of millimeter waves. This article proposes a hybrid field reconstruction framework that integrates classical electromagnetic algorithms with deep learning to evaluate the IPD of wireless communication devices operating at 30 GHz, thereby determining compliance with established RF exposure limits. An initial estimate of the electric field on the evaluation plane is obtained using a classical reconstruction algorithm, followed by refinement through a neural network model that learns the mapping between the initial and accurate values. A multiantenna dataset, generated via full-wave simulation, is used for training and testing. The impacts of training strategy, initial-value algorithm, reconstruction distance, and measurement sampling density on model performance are analyzed. Results show that the proposed method significantly improves reconstruction accuracy, achieving an average relative error (RE) of 4.57% for electric field reconstruction and 0.12 dB for peak spatial-average IPD estimation on the test dataset. Additionally, the effects of practical uncertainty factors, including probe misalignment, interprobe coupling, and measurement noise, are quantitatively assessed.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Cao, M., Liu, Z., Matkerim, B., Wu, T., Li, C., Zong, Y., & Qi, B. (2026). Field Reconstruction for High-Frequency Electromagnetic Exposure Assessment Based on Deep Learning. IEEE Transactions on Antennas and Propagation, 74(7), 6954-6966. https://doi.org/10.1109/tap.2026.3681071

Vancouver

Cao M, Liu Z, Matkerim B, Wu T, Li C, Zong Y, et al. Field Reconstruction for High-Frequency Electromagnetic Exposure Assessment Based on Deep Learning. IEEE Transactions on Antennas and Propagation. 2026;74(7):6954-6966. doi:10.1109/tap.2026.3681071

BibTeX
@article{Cao2026,
  author = {Cao, Miao and Liu, Zicheng and Matkerim, Bazargul and Wu, Tongning and Li, Changyou and Zong, Yali and Qi, Bo},
  title = {Field Reconstruction for High-Frequency Electromagnetic Exposure Assessment Based on Deep Learning},
  journal = {IEEE Transactions on Antennas and Propagation},
  year = {2026},
  volume = {74},
  number = {7},
  pages = {6954--6966},
  doi = {10.1109/tap.2026.3681071}
}
Kostenlos starten →