Estimation of the Scattering Parameter at the Resonance Frequency of the UHF Band of the E-Shaped RFID Antenna Using Machine Learning Techniques

In this paper, a study on the estimation of the scattering parameters of the operating resonance frequency in the Ultra High Frequency (UHF) band of the E-shaped RFID antenna with machine learning based models has been made. The dataset used in this work consisting of 2592 samples in total has been obtained from the simulation program as a result of a parametric study of the parameters that constitute the antenna design. Different machine learning algorithms have been applied on two different output data types of the same parameter, complex and linear scattering parameters, and the predictive performance of the models have been compared. Polynomial regression technique has been used to estimate the linear scattering parameter and the R
²
score of this model 99.906% and the mean squared error value 0.001. For complex parts of the scattering parameter, the Multi Output Regression technique has been applied for real and imaginary values and the R
²
score of this model 98.66%, and the mean squared error value 0.007.