Diagonal L-Shaped Slotted Antenna Design for 2.4 GHz Wireless Applications with Machine Learning Based Reflection Coefficient Calculator GUI

In this study, a machine learning assisted microstrip antenna design for a 2.4 GHz Wi-Fi frequency band has been designed and numerically calculated. The proposed antenna design has been carried out using an electromagnetic field solver CST, different design parameters have been determined and because of parametric calculation, data suitable for machine learning algorithms have been obtained. According to the different values of 4 design parameters, 625 different antenna reflection coefficients at the 2.4 GHz frequency band were obtained in linear and decibel forms for the machine learning-based design. 4 different machine learning regression algorithms (linear regression, support vector regression, decision tree, and random forest) have been used to estimate the reflection coefficient at 2.4 GHz. The machine learning results have been examined, it has been achieved that the best prediction performance model had R2 value of 0.8 and a mean squared error value of 0.2 for the S11 in dB form, and R2 value of 0.98 and a mean squared error value of 0.02 for the linear S11. In addition, a PyQt based graphical user interface is presented, which can instantly estimate the reflection coefficient with different machine learning techniques depending on the design parameters of the proposed antenna.