Optimization of Circular Loop Antenna With Step Change in Loop Width Using Machine Learning Techniques

Abstract

In the fast-paced world, the effectiveness of wireless communication for seamless connectivity relies on the performance of antennas. Presently for accurate real-time data transfer and for diverse wireless communication applications, optimizing various antenna parameters is becoming essential. Emerging machine learning (ML) techniques provide a platform to avoid the design gap to explore the required antenna performance parameters for effective data transfer. To overcome the time constraints in the conventional electromagnetic (EM) simulators in optimizing, the antenna parameters for any antenna design have driven innovation into the realm of ML algorithms. This chapter proposes the design and optimization of a C-shaped Circular loop antenna using e-Xtreme gradient boost (XGBoost) regressor model.