Abstract
The performance of wireless networks is related to the optimized structure of the antenna. Therefore, in this paper, a Machine Learning (ML)-assisted new methodology named Self-Adaptive Bayesian Neural Network (SABNN) is proposed, aiming to optimize the antenna pattern for next-generation wireless networks. In addition, the statistical analysis for the presented SABNN is evaluated in this paper and compared with the current Gaussian Process (GP). The training cost and convergence speed are also discussed in this paper. In the final stage, the proposed model's measured results are demonstrated, showing that the system has optimized outcomes with less calculation time.