Hibah Muhammed
Department of Electrical and Electronic Engineering, Faculty of Engineering, University of Benin, Benin City, Nigeria

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Physics-Informed Artificial Intelligence for Adaptive Wireless Channel Modelling in Fifth-Generation (5G) Networks Aniru Abudu Muhammed; Hibah Muhammed
International Journal of Research and Applied Technology Vol. 5 No. 2 (2025): December 2025
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v5i2.18015

Abstract

Accurate wireless channel modeling is foundational to the design and optimization of fifth-generation (5G) communication systems. Although traditional geometry-based stochastic models (GBSMs) and empirical formulations are effective in static environments, they frequently fail to capture the nonlinear, non-stationary, and environment-dependent propagation behaviors inherent in modern multi-antenna and millimeter-wave systems. This study introduces a hybrid physics-informed artificial intelligence (AI) framework that fuses physical propagation principles with deep learning architectures, yielding a channel modeling approach that is interpretable, adaptive, and data-efficient. Leveraging large-scale datasets, including DeepMIMO, COST (Cooperation in Science and Technology) 2100, and New York University (NYU) Wireless, the proposed model integrates Physics-Informed Neural Networks (PINNs) and Convolutional Neural Networks (CNNs) to concurrently capture spatial, temporal, and frequency-domain relationships within realistic propagation environments. Furthermore, the incorporation of reinforcement and federated learning layers facilitates real-time adaptation and decentralized training across multiple base stations while strictly preserving data privacy. Empirical evaluations demonstrate substantial improvements over established benchmark models, such as 3GPP (3rd Generation Partnership Project) TR 38.901, COST 2100, and QuaDRiGa (QUAsi Deterministic RadIo Channel GenerAtor), achieving an RMSE of 1.72 dB and an NMSE of –20.6 dB, which correspond to a 25–30% gain in accuracy. Visual analyses of power delay profiles, residual error distributions, and spatial correlation maps further corroborate the model's robustness and physical consistency. Ultimately, the proposed framework establishes a scalable, interpretable, and adaptive paradigm for next-generation wireless channel modeling, paving the way toward intelligent, self-optimizing, and 6G-ready communication networks that bridge the gap between physics-based theory and AI-driven modeling.