Citation

Haque, Md. Ashraful and Ananta, Redwan A. and Nahin, Kamal Hossain and Tiang, Jun Jiat and Singh, Narinderjit Singh Sawaran and Alsulami, Ruwaybih and Alzahrani, Saeed (2026) Quad port MIMO antenna design for WLAN and N78 application using regression machine learning validation. Scientific Reports, 16 (1). ISSN 2045-2322

Text s41598-026-64832-x.pdf - Published Version Restricted to Repository staff only Download (6MB)

Abstract

This paper presents the design and analysis of a compact four-port MIMO antenna intended for 5G communication systems, specifically targeting the n78 band (3.5 GHz) and the WLAN band (5.25 GHz). The proposed antenna has dimensions of 88.2 mm × 88.2 mm (1.03λ0 × 1.03λ0). It achieves peak gains of 6.22 dB and 6.55 dB at its respective resonance frequencies, with a high isolation of − 28 dB between ports. The antenna covers bandwidths of 0.3 GHz (8.70%) and 0.37 GHz (7.07%) at 3.5 GHz and 5.25 GHz, respectively, with an Envelope Correlation Coefficient (ECC) of 0.006 and Diversity Gain (DG) of 9.99 dB, ensuring excellent MIMO performance. The antenna is simulated using CST Studio Suite and designed to offer high gain and low return loss, suitable for 5G and WLAN applications. Additionally, an RLC equivalent circuit model is developed in the ADS Agilent software, where the resonance frequencies closely match those obtained from full-wave simulations. To further validate and predict the antenna’s performance characteristics, a supervised machine learning (ML) regression model is applied. The model’s accuracy is evaluated using several performance metrics, including the variance score, R-squared (R2), mean squared error (MSE), mean absolute error (MAE), root mean square error (RMSE), and mean squared logarithmic error (MSLE).

Item Type:	Article
Uncontrolled Keywords:	N78, 5G, MIMO antenna, CST, Machine learning Industrial and Innovation
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 Suzilawati Abu Samah
Date Deposited:	28 Oct 2026 08:26
Last Modified:	28 Oct 2026 08:26
URII:	http://shdl.mmu.edu.my/id/eprint/16957

Downloads

Edit (login required)