EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial Intelligence for Advanced 5G MIMO Channel Communications

Mohammad Serajuddin, Syed Ahad Murtaza Alvi

International Journal of Information Technology & Computer Sciences Perspectives · 30.06.2026 · 15 (1) · 10-17

DOI: 10.67591/itcs2026.15.1.58 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Information Technology & Computer Sciences Perspectives, online erschienen am 30.06.2026. Verfasst von Mohammad Serajuddin und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

This study investigates the application of Artificial Intelligence (AI) techniques for enhancing beamforming and channel communication performance in fifth-generation (5G) Multiple-Input Multiple-Output (MIMO) systems. It evaluates the effectiveness of machine learning algorithms in improving channel state estimation, communication reliability, and system efficiency while addressing the challenges associated with high-dimensional wireless communication environments. Theoretical Framework: The study is grounded in the concepts of 5G MIMO-OFDM communication, beamforming optimization, channel state estimation, and Artificial Intelligence-based wireless communication. It integrates machine learning techniques with Principal Component Analysis (PCA) for feature extraction to improve channel modelling and communication performance under complex propagation conditions. Methodology: A comparative experimental research approach was adopted to evaluate three supervised machine learning algorithms—JRip, J48 Decision Tree, and Naïve Bayes—for channel estimation in a 5G MIMO-OFDM environment. Principal Component Analysis (PCA) was applied to reduce the dimensionality of channel-state data, while model performance was assessed under different feature configurations with and without Post-Signal-to-Interference-plus-Noise Ratio (Post-SINR) information. Classification accuracy served as the primary performance metric for comparative evaluation.

Findings

The experimental results demonstrate that AI-based machine learning methods outperform conventional calibration techniques for channel estimation. Among the evaluated classifiers, the Naïve Bayes algorithm achieved the highest classification accuracy, reaching approximately 97.98%, and maintained stable performance even when Post-SINR information was unavailable. JRip and J48 exhibited lower classification accuracy and greater dependence on feature selection and Post-SINR information. The findings indicate that dimensionality reduction through PCA improves computational efficiency while supporting accurate AI-driven channel estimation for 5G MIMO communications. Research Implications: The study provides practical guidance for researchers and wireless communication engineers by demonstrating the potential of AI-based channel estimation techniques to enhance beamforming, spectral efficiency, and communication reliability in next-generation mobile networks. The findings also encourage further research on advanced deep learning and hybrid AI models for intelligent 5G and future 6G communication systems. Value: This study contributes to the advancement of AI-enabled wireless communications by integrating Principal Component Analysis with comparative machine learning techniques for channel estimation in 5G MIMO-OFDM systems. The proposed analytical framework highlights the effectiveness of AI in improving communication performance while providing a practical basis for future intelligent beamforming and adaptive wireless network optimization.

Zitieren

APA

Serajuddin, M., & Alvi, S. A. M. (2026). Artificial Intelligence for Advanced 5G MIMO Channel Communications. International Journal of Information Technology & Computer Sciences Perspectives, 15(1), 10-17. https://doi.org/10.67591/itcs2026.15.1.58

Vancouver

Serajuddin M, Alvi SAM. Artificial Intelligence for Advanced 5G MIMO Channel Communications. International Journal of Information Technology & Computer Sciences Perspectives. 2026;15(1):10-17. doi:10.67591/itcs2026.15.1.58

BibTeX
@article{Serajuddin2026,
  author = {Serajuddin, Mohammad and Alvi, Syed Ahad Murtaza},
  title = {Artificial Intelligence for Advanced 5G MIMO Channel Communications},
  journal = {International Journal of Information Technology & Computer Sciences Perspectives},
  year = {2026},
  volume = {15},
  number = {1},
  pages = {10--17},
  doi = {10.67591/itcs2026.15.1.58}
}
Kostenlos starten →