Machine Learning Approach for a Perturbed Rectangular Patch Antenna for 11 GHz Application

This work provides an edge slotted patch antenna in which a normal rectangular patch has been considered and slots have been introduced at the edge of the patch. The comparison of parameters such as <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$S_{11}$</tex>, VSWR have been done after implementing the slots. 11 GHz frequency is considered as design frequency for proposed patch. Resonant frequency after slot implementation has been found to be 11 GHz with −10 dB bandwidth of 1 GHz with antenna gain of 4.5 dB. Four slots of varying width have been placed on the proposed patch. Three different machine learning algorithms have been utilized for slot width optimization and parameters like MAE, MSE, RMSE and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R}^{\mathbf{2}}$</tex> have been evaluated. The suggested antenna can be employed for 11 GHz applications that includes point-to-point communication and 6G. FR4 Epoxy material is chosen as substrate material.