19 October 2023 in Food Control
1 September 2021 in Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy
24 April 2023 in Analytica Chimica Acta
27 March 2023 in Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy
1 May 2026 in IEEE Transactions on Vehicular Technology
This paper presents a data-efficient optimization framework for compact MIMO antenna decoupling in space constrained vehicular communications. To address the challenges of mutual coupling and limited training data, a three-stage data generation pipeline is proposed, including frequency-aware data partitioning, a multibranch encoder-assisted conditional generative adversarial network, and a dual-filtering strategy for quality assurance. High-fidelity generated data are used to train forward and inverse surrogate models, enabling fast and accurate antenna design optimization without repeated electromagnetic simulations. Applied to a broadband stacked patch antenna array, the optimized design achieves a measured isolation of –42.75 dB and meets bandwidth and reflection criteria. Compared with traditional simulation-based methods, the proposed framework reduces the full-wave simulation time for data generation by 83.43%. These results highlight the potential of combining generative modeling and surrogate learning for intelligent and efficient antenna design in next-generation vehicular MIMO systems.
13 April 2026 in IEEE Transactions on Microwave Theory and Techniques
This article proposes a novel reflected phase-regulated metasurface (RPMS) integrated with a position-aware encoder-only transformer (PEformer). The RPMS employs geometrically tunable stub-loaded reflector units to control the phase of reflected wave without altering its amplitude. This facilitates the effective coupling suppression under stringent height constraints while preserving the matching condition. The operating principle of RPMS is elucidated through the theoretical analysis and numerical simulations. In parallel, the PEformer leverages the position attention and multihead self-attention (MHSA) mechanisms to effectively capture structural correlations and accurately predict optimal design parameters from target electromagnetic (EM) responses. To validate the proposed approach, a compact wideband stacked patch antenna prototype with only 2-mm edge-to-edge spacing is selected as a verification case and fabricated. Measurement results demonstrate that the RPMS achieves up to 29 dB of isolation improvement and a 17% decoupling bandwidth, with negligible degradation in the impedance matching, gain, and radiation patterns. Additional performance metrics, including envelope correlation coefficient (ECC), diversity gain (DG), and total active reflection coefficient (TARC), confirm the enhanced diversity performance and minimal efficiency loss. Combining clear physical insights with a simple and scalable optimization framework, the proposed RPMS offers a promising pathway for implementing broadband, low-profile coupling suppression not only in antenna systems but also in a broad range of densely integrated microwave devices.