A compact dual-frequency ( $38/60 \mathrm{GHz}$ ) microstrip patch antenna with novel design is proposed for 5G mobile handsets to combine complicated radiation mechanisms for dual-band operation. The proposed antenna is composed of two electromagnetically coupled patches. The first patch is directly fed by a microstrip line and is mainly responsible for radiation in the lower band ( $38 \mathrm{GHz}$ ). The second patch is fed through both capacitive and inductive coupling to the first patch and is mainly responsible for radiation in the upper frequency band ( $60 \mathrm{GHz}$ ). Numerical and experimental results show good performance regarding return loss, bandwidth, radiation patterns, radiation efficiency, and gain. The impedance matching bandwidths achieved in the $38 \mathrm{GHz}$ and $60 \mathrm{GHz}$ bands are about $2 \mathrm{GHz}$ and $3.2 \mathrm{GHz}$ , respectively. The minimum value of the return loss is $-42$ dB for the $38 \mathrm{GHz}$ band and $-47$ for the $60 \mathrm{GHz}$ band. Radiation patterns are omnidirectional with a balloon-like shape for both bands, which makes the proposed single antenna an excellent candidate for a multiple-input multiple-output (MIMO) system constructed from a number of properly allocated elements for 5G mobile communications with excellent diversity schemes. Numerical comparisons show that the proposed antenna is superior to other published designs.

Breast cancer detection through non-invasive and accurate techniques remains a critical challenge in medical diagnostics. This study introduces a deep learning-based framework that leverages a microwave radar system equipped with an arc-shaped array of six antennas to estimate key tumor parameters, including position, size, and depth. This research begins with the evolutionary design of an ultra-wideband octagram ring patch antenna optimized for enhanced tumor detection sensitivity in directional near-field coupling scenarios. The antenna is fabricated and experimentally evaluated, with its performance validated through S-parameter measurements, far-field radiation characterization, and efficiency analysis to ensure effective signal propagation and interaction with breast tissue. Specific Absorption Rate (SAR) distributions within breast tissues are comprehensively assessed, and power adjustment strategies are implemented to comply with electromagnetic exposure safety limits. The dataset for the deep learning model comprises simulated self and mutual S-parameters capturing tumor-induced variations over a broad frequency spectrum. A core innovation of this work is the development of the Attention-Based Feature Separation (ABFS) model, which dynamically identifies optimal frequency sub-bands and disentangles discriminative features tailored to each tumor parameter. A multi-branch neural network processes these features to achieve precise tumor localization and size estimation. Compared to conventional attention mechanisms, the proposed ABFS architecture demonstrates superior prediction accuracy and interpretability. The proposed approach achieves high estimation accuracy and computational efficiency in simulation studies, underscoring the promise of integrating deep learning with conformal microwave imaging for safe, effective, and non-invasive breast cancer detection.