Numerical and experimental generated data during project https://doi.org/10.1038/s41598-024-80182-y

The dataset was generated using a machine learning procedure for cost-effective global optimization-based miniaturization of antennas. The technique included parameter space pre-screening and the iterative refinement of kriging surrogate models using the predicted merit function minimization as an infill criterion. Numerical experiments conducted on four broadband antennas indicated that the proposed framework consistently yielded competitive miniaturization rates across multiple algorithm runs at low costs, compared to the benchmark.