This study introduces a machine learning (ML)-driven approach to next-generation microwave filter design that enhances both accuracy and efficiency via repeated refinement. The approach includes generating a coupling matrix from filter specifications, followed by predicting physical parameters such as iris widths and resonator lengths using ML models, especially with the XGBoost algorithm. These predictions are validated and tuned via simulations and iterative adjustments to ensure meeting the performance criteria, such as center frequency, bandwidth, and return loss. For tuning, in this work, we used Simulated Annealing to extract a coupling matrix to reduce errors and hence allow accurate further optimization. The predicted values before optimization are more than 90 percent accurate compared to the optimized values, significantly reducing the optimization time and the number of iterations required. To demonstrate the procedure’s validity, third-, fourth-, and fifth-order filters are implemented, which shows significant improvements in design efficiency and accuracy.

This paper presents a compact four-port multiple-input multiple-output (MIMO) antenna operating in the Ku-band around 13 GHz, targeting early-phase 6G upper-midband front-end applications. The proposed antenna employs orthogonally arranged short-ended square patch elements combined with a modified defected ground structure (DGS) to achieve high port isolation and compact footprint. A prototype fabricated on Rogers RO4350 substrate demonstrates good agreement between simulated and measured results. The antenna achieves $|S_{11}|$ < −10 dB over 12.9–13.1 GHz band, inter-port isolation exceeding 25 dB, and an envelope correlation coefficient (ECC) below $0.01$. The measured realized gain reaches 7.02 dBi with a radiation efficiency above 80%. Compared with recent Ku-band MIMO antennas, the proposed design provides a 45% size reduction while maintaining high isolation at a close element spacing of 0.25${\lambda }_0$. The proposed antenna intentionally adopts a narrowband operating characteristic, reflecting a design trade-off that prioritizes compact size, high isolation, and low spatial correlation over wideband performance. These features make the antenna well suited for early-stage 6G-oriented front-end modules, fixed wireless access, backhaul links, and short-range sensing systems operating in the upper-midband frequency range.