EUVIMEDEUVIMED entdecken
Crossref

A High‐Performance 3D Eight‐Port THz‐MIMO Antenna System Verified With Machine Learning for Enhanced Wireless Communication Systems

Samir Salem Al‐Bawri, Wazie M. Abdulkawi, Abdel‐Fattah A. Sheta, Md. Moniruzzaman

International Journal of Communication Systems · 10.03.2025 · 38 (4)

DOI: 10.1002/dac.6006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Communication Systems, online erschienen am 03.10.2024. Verfasst von Samir Salem Al‐Bawri und 3 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Prince Sattam bin Abdulaziz University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article proposes an eight‐port octagonal‐shaped multiple‐input multiple‐output (MIMO) wideband 3D antenna system for terahertz (THz) applications. The 3D configuration of the proposed THz‐MIMO antenna is placed on a 55‐μm‐thick polyimide substrate. A modified butterfly‐shaped radiating patch and full ground plane make up the single antenna element. Every antenna element spans a wide impedance bandwidth for THz spectrums from 0.9‐ to 1.68‐THz frequency band, a frequency operating range with the highest radiation efficiency of 98% and is printed in a compact size of 130 × 110 μm 2 (0.00004 × 0.00005 , with respect to the lowest operating frequency). The THz‐MIMO antenna system with eight ports is composed of both symmetric and nonsymmetric array arrangements. For configurations that are symmetric or nonsymmetric, the estimated MIMO performance parameters, envelope correlation coefficient (ECC) < 0.01 within allowable bounds, diversity gain (DG) exceeding 9.99 dB, total active reflection coefficient (TARC) < −10 dB, and channel capacity loss (CCL) below 0.2 bits/s/Hz, and the exhibited gain is above 7.5 dBi. Furthermore, another approach, such as supervised regression machine learning (ML), is used to forecast antenna gain. The variance score, mean square error (MSE), root mean square error (RMSE), R square, mean squared logarithmic error (MSLE), mean absolute error (MAE), and so forth are used to gauge how well ML models perform. The accuracy of ridge regression gain prediction is approximately 98%, with errors of less than unity, which is better than the other ML models. The suggested THz‐MIMO antenna system is appropriate for the wireless communication networks operating in the sixth generation.

Förderung

  • Prince Sattam bin Abdulaziz University

Zitieren

APA

Al‐Bawri, S. S., Abdulkawi, W. M., Sheta, A. A., & Moniruzzaman, M. (2025). A High‐Performance 3D Eight‐Port THz‐MIMO Antenna System Verified With Machine Learning for Enhanced Wireless Communication Systems. International Journal of Communication Systems, 38(4). https://doi.org/10.1002/dac.6006

Vancouver

Al‐Bawri SS, Abdulkawi WM, Sheta AA, Moniruzzaman M. A High‐Performance 3D Eight‐Port THz‐MIMO Antenna System Verified With Machine Learning for Enhanced Wireless Communication Systems. International Journal of Communication Systems. 2025;38(4). doi:10.1002/dac.6006

BibTeX
@article{AlBawri2025,
  author = {Al‐Bawri, Samir Salem and Abdulkawi, Wazie M. and Sheta, Abdel‐Fattah A. and Moniruzzaman, Md.},
  title = {A High‐Performance 3D Eight‐Port THz‐MIMO Antenna System Verified With Machine Learning for Enhanced Wireless Communication Systems},
  journal = {International Journal of Communication Systems},
  year = {2025},
  volume = {38},
  number = {4},
  doi = {10.1002/dac.6006}
}
Kostenlos starten →