Machine Learning-Enhanced Asymmetric CPW-Fed Dual Band Antenna for Wireless Applications

An innovative asymmetric CPW-fed dual-band antenna augmented by machine learning is presented in this study. It is designed for wireless applications, particularly WLAN and WiMAX. The physical dimensions of the antenna were optimized to produce improved impedance matching, bandwidth, and radiation efficiency by incorporating machine learning techniques like KNN and Random Forest. The proposed antenna, which incorporates metamaterial structures, operates efficiently across its target frequency bands. Simulation and experimental results demonstrate a bandwidth increase from 0.36 GHz to 2.36 GHz, a gain improvement from 0.12 dBi to 0.54 dBi, and a return loss enhancement with values reaching -27.03 dB compared to traditional designs. These findings confirm the efficacy of ML-driven optimization in antenna design.