Dual-Band High Tuning Range Frequency Reconfigurable Cylindrical Dielectric Resonator Antenna for n7, n30, n38, n40, n41, n46, n47, n53 and n79 5G New Radio Application with Machine Learning Approach.

A dual-band frequency reconfigurable cylindrical dielectric resonator antenna (DRA) for 5G New Radio (NR) application within a Sub-6 GHz is presented in the proposed work. In this work, nine n7, n30, n38, n40, n41, n46, n47, n53 and n79 5G NR bands are presented. A novel approach for 5G NR bands has been presented to provide dual-band capabilities and frequency reconfigurability with machine learning (ML). We achieve this reconfigurability by using two PIN diode switches that operate in various configurations, allowing for a maximum wide tuning range of 80.19%. In cylindrical DRA HEM11δ\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\text{HEM}}_{11\delta }$$\end{document} and HEM12δ\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\text{HEM}}_{12\delta }$$\end{document} modes are responsible for dual-band operation. The K-nearest neighbor (KNN) ML technique achieves an accuracy of more than 98%, as compared to artificial neural network (ANN), random forest (RF), extreme gradient boosting (XGB), and decision tree (DT) across all configurations for the S11\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$S_{11}$$\end{document} prediction. [ABSTRACT FROM AUTHOR]