Citation

Khan, Irfan Ullah and Roslee, Mardeni and Mohd Hassan, Siti Maisurah and Ali, Farman and Ullah, Yasir and Kabir, Fardin (2025) UAV-to-Ground Communication Channel Characterization with Frequency Dependency in Built-Up Environments. In: 2025 International Conference on Engineering and Emerging Technologies (ICEET), 22-23 October 2025, Kuala Lumpur, Malaysia.

Text 1.pdf - Published Version Restricted to Repository staff only Download (10MB)

Abstract

The modeling of UAV-to-Ground (U2G) Communication channels is important for reliable connectivity in frequency-selective built-up environments. Existing models are limited by scattering structures, static UAV configurations, and the absence of frequency-dependent multi path characterization. This work introduces a channel characterization model that integrates geometric features of built-up environment with a data-driven framework. A Graph Neural Network (GNN) is trained to capture spatial-temporal dependencies in channel impulse responses, while the Grasshopper Optimization Algorithm (GOA) is employed to tune channel parameters including delay spread, coherence bandwidth, and angular dispersion. The proposed model achieves high accuracy in predicting frequency-selective fading patterns under UAV mobility across diverse urban layouts, outperforming traditional analytical and semi-empirical approaches.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	UAV-to-Ground Communication, built-up environments, frequency-selective fading, Graph Neural Network, Grasshopper Optimization Algorithm
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	20 Apr 2026 00:57
Last Modified:	20 Apr 2026 00:57
URII:	http://shdl.mmu.edu.my/id/eprint/15737

Downloads

Edit (login required)