Design of Rectangular Dielectric Resonator Antenna for Artificial Neural Network

This paper represents a study of simulation of a Dielectric Resonator Antenna (DRA) based on its rectangular shape for Artificial Neural Network (ANN). The DRA is intended to be used as the radiating element of a transmitting array of active integrated antennas; its input impedance must exhibit a proper resistive load at the fundamental resonance frequency, as well as a dominant reactive behavior, either inductive or capacitive, at higher harmonics. The design procedure is performed by exploiting Artificial Neural Networks (ANN), to find the resonator geometry starting from the desired resonance frequency, and a finite element based numerical tool for the electromagnetic characterization of the antenna. The ANN can be employed in a designed RDRA over a short range of frequency of 5.68-5.9 GHz. After simulation this network can give a broad acceptance of simulated data of input and output dimensions of DRA with the possible original existence of the corresponding