Comparative Analysis of Machine Learning Techniques for Resonant Frequency Prediction for Printed Microstrip Antennas

One of the most often utilized clever techniques for antenna modelling is machine learning. In this study, novel approaches based on supervised machine learning is developed for calculating the resonance frequency of printed microstrip antennas with regular geometries. Elastic Net Regression Algorithms, Random Forest, and LASSO are the three supervised machine learning algorithms that are used to train, test, and predict resonance frequencies. The findings of the supervised machine learning techniques exceeded those of other approaches presented in the literature for the resonance frequency of the circular MSAs (C-MSAs), triangular MSAs (T-MSAs), and rectangular MSAs (R-MSAs).