Citation

Haque, Md. Ashraful and Ahmed, Md. Kawsar and Nirob, Jamal Hossain and Hasan, Mehidy and Tiang, Jun Jiat and Singh, Narinderjit Singh Sawaran and Nahas, Mouaaz and Nahas, Mousaab M. (2026) High-performance 28 GHz MIMO antenna design for 5G applications and regression machine learning validation. Discover Applied Sciences, 8 (9). ISSN 3004-9261

Text s42452-026-08969-4.pdf - Published Version Restricted to Repository staff only Download (6MB)

Abstract

Wireless communication has become indispensable to our lives and will continue to drive the development of Mobile Communication (MC), including the Internet of Things (IoT), and Intelligent Transportation Systems (ITS). Wireless systems face challenges such as increased data transmission, reliability, and improved user experience. To meet the demands of future wireless solutions like 5G, researchers are investigating the millimeter-wave (mm-wave) frequencies. High-frequency 5G in the mm-wave region can support multi-Gbps data rates with low delay and much greater bandwidth than lower frequencies. This antenna design uses the 4-port concept, careful material selection, and precise fabrication and simulation. The design achieves an impedance bandwidth of about 3.24 GHz, a peak gain of nearly 7.92 dB,, radiation efficiency close to 99%, and isolation better than −30 dB. Applying machine learning in antenna design shows significant promise for optimizing performance in 5G and future wireless systems. Results show that Extra Trees Regression outperforms other algorithms, achieving the lowest error metrics and the highest coefficient of determination (R²) value of 91.17%. The findings highlight the potential of machine learning to enhance the optimization and scalability of antenna designs for nextgeneration wireless communication systems.

Item Type:	Article
Uncontrolled Keywords:	5G, 28 GHz
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 Sep 2026 02:56
Last Modified:	04 Sep 2026 02:56
URII:	http://shdl.mmu.edu.my/id/eprint/16692

Downloads

Edit (login required)