Estimation of S11 Values of Patch Antenna Using Various Machine Learning Models

Abstract

Compact, wide-band, high efficiency, multiband, and relatively affordable antennas are required by recent advancements in wireless communications for use in modern applications. This work shows how machine learning methods can be used to predict the S11 (return loss) parameters of microstrip patch antenna. The same dimensions were used throughout the design process. The simulated dataset is utilized to create a Machine Learning model, which is then applied to predict the S11 values. The machine learning models like Decision Tree, Random Forest, XG Boost & KNN is also developed using the same dataset. When the anticipated result is compared, it is shown that the model using KNN yields superior results.