Deep graphene based reconfigurable circularly polarized star-shaped microstrip antenna design at terahertz frequencies for biomedical application

Next generation wireless communication (WC) needs high-performance which assist high-speed data transmission while meeting the requirements for low profile, weight and cost. Several researchers introduce graphene-based circular, triangular, square and hexagonal antenna for WC in the terahertz (THz) resonant frequency (RF). This research work introduces a deep graphene based reconfigurable circularly polarized star-shaped microstrip antenna at 2.98 THz frequency for biomedical application. Graphene has been applied in the structure of star-shaped microstrip antenna. This reconfigurable circularly polarized graphene-based antenna is obtained on a SiO 2 substrate. The introduced circularly polarized antenna has a single feed and an easy design. The major objective of this research work is to propose graphene material as an efficient solution in designing antenna for organizing and adjusting its polarization. Because of the complexity of the structure of graphene antenna, enhanced scalable graph random improved Fick’s law neural networks is applied for predicting the antenna parameters. This proposed method is a combination of enhanced scalable graph random neural network (ESGRNN) and an improved Fick’s law optimization which is used to optimize the prediction error of the proposed ESGRNN. To prevent premature incomplete convergence in the traditional Fick's law algorithm, a dynamic lens-imaging learning strategy is incorporated. Finally, the achieved prediction accuracy is 98%, the mean square error is 2%, minimal return loss (S11) is − 55.98 dB, impedance bandwidth is 800 GHz, gain is 9.8 dB, and voltage standing wave ratio is 1.011 at 2.98 THz RF. As a result, the designed antenna is well-suitable for biomedical applications like riboflavin detection.