Performance prediction of a circularly polarized graphene-dielectric resonator-based antenna for THz frequency application using machine learning algorithms.

ABSTRACT

In this article, a graphene-dielectric resonator-based antenna is designed in the THz frequency regime. Circular polarization is achieved by feeding the cylindrical-shaped ceramic using a perturbed square-shaped aperture. Graphene loading over the alumina ceramic provides the frequency reconfigurable feature. In order to overcome the difficulty of simulating the THz antenna (i.e., very large simulation time), machine learning algorithms such as the artificial neural network (ANN) and random forest are used to effectively predict the performance of the designed antenna. The proposed antenna works effectively in between 5.0 and 5.5 THz with a 3 dB axial ratio frequency range from 5.1 to 5.35 THz. There is good correlation found between the predicted, measured, and simulated reflection coefficient and axial ratio. Due to stable radiation properties and good diversity performance within the operating frequency band, the proposed antenna can be employable for different wireless applications in the THz frequency regime.