Machine Learning-Driven Control and Optimization of Dual Band-Notched UWB Circular Monopole Antenna

As communication technologies continue to advance rapidly, there is a growing need for antennas that provide high performance while minimizing interference from other systems. This paper explores optimizing and controlling the performance of a dual band-notched Ultra-Wideband (UWB) circular monopole antenna with parasitic resonators using machine learning techniques. Building upon a previously proposed antenna design, we first employ various machine learning models—such as Gaussian Process Regression, Support Vector Regression, and Gradient-Boosted Trees—to precisely control band notches within specific frequency ranges, thereby preventing interference with any narrow-band systems in close vicinity. Following this, we leverage a new method for evaluating the performance of UWB antennas with band-notched characteristics and use similar models to optimize the antenna’s physical properties and enhance radiation characteristics. Validated through simulations in CST Studio Suite, the optimized antenna demonstrates significantly improved return loss, and our approach allows for accurate prediction of the physical properties required to achieve desired band notches within the 4–8 GHz and 6–9 GHz ranges, corresponding to each parasitic resonator.