Machine Learning Optimized Trident Monopole Antenna for WLAN/WiMAX Applications

View at publisher Summarise with VIRAT
Authors: Debajyoti Chatterjee, Anjan Kumar Kundu, Suchanda Chatterjee
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper introduces a machine learning (ML) optimization framework for the design of a high-performance, trident-shaped monopole antenna targeting$2.4 / 2.5\ \text{GHz}$WLAN and 5.2 GHz WiMAX applications. The complex geometry of the trident structure, which generates dual-band operation through its central and side arms, presents a multi-parameter design challenge. Traditional design methods rely on iterative simulation and are often computationally prohibitive. To overcome this, a data-driven surrogate modeling approach is implemented. Key geometric parameters of the trident element are used as inputs to train multiple regression models, including linear regression, Support Vector Regression, and Gaussian Process Regression (GPR), to predict antenna performance metrics. The GPR model demonstrated superior accuracy and was employed to determine the optimal geometry that maximizes gain and bandwidth while minimizing return loss. The trident monopole antenna achieves a measured impedance bandwidth of 360 MHz and 340 MHz at the lower and higher bands, respectively, with stable radiation patterns and gains of 1.94 dBi (lower band) and 3.28 dBi (upper band). Furthermore, the ML optimized antenna provides higher bandwidth (760 MHz in lower band and 1 GHz in upper band) and gain (2.39 dBi in lower band and 4.11 dBi in upper band) that significantly reduces the design cycle time for complex antenna structures, ensuring performance that meets stringent modern wireless communication standards.

Fields of Study & Subjects

Antenna Design and Analysis Antenna Design and Optimization Advanced Antenna and Metasurface Technologies

Publication details

Journal / source
International Conference on Electronics, Materials Engineering & Nano-Technology (IEMENTech)
Pages
1–6
Publication date
6 February 2026
Language
EN