This article presents a meta-surface-based antenna configuration aimed at enhancing the gain performance for millimeter-wave wireless communication systems. The proposed structure consists of a rectangular meta-surface with circular cut-outs placed beneath a rectangular ring to improve the electromagnetic characteristics of the antenna. A rectangular monopole antenna is designed to operate at dual frequency bands around 38 GHz and 43 GHz. To further enhance radiation performance, Artificial Magnetic Conductor (AMC) structures are incorporated beneath the antenna element. The AMC surface improves the radiation efficiency and stabilizes the antenna characteristics by providing in-phase reflection near the operating frequencies. Simulation results demonstrate that the integration of the AMC structure significantly enhances the antenna gain and impedance matching performance. In particular, the incorporation of a $4\times 4$ AMC array increases the antenna gain from approximately 3.4 dB to 6.4 dB while maintaining stable reflection coefficient characteristics. The proposed design demonstrates improved gain performance and compact structure, making it a promising candidate for millimeter-wave wireless communication applications.

Satellite imagery is increasingly being scrutinized through deep learning methodologies for remote sensing applications, particularly focusing on the detection of water bodies. Identification and analysis of rivers, lakes, and reservoirs through segmentation have become feasible, enabling the exploration of their statistical information. During crises such as floods and changes in river pathways, real-time detection of water bodies via remote sensing proves to be highly advantageous. Nevertheless, achieving precise segmentation of water bodies presents a notable challenge, mainly due to the necessity of high-resolution multi-channel satellite images. Existing literature predominantly relies on satellite data from multi-band satellites for water-body extraction. Conversely, the current research emphasizes the segmentation of water-body regions using relatively lower-resolution RGB images without the incorporation of extra multi-spectral channels. To tackle this challenge, a unique methodology is suggested, involving a customized U-Net model integrated with a time-frequency attention network for segmentation. To assess the comprehensive performance of the proposed model, it is evaluated against a publicly available Sentinel-2 satellite dataset, and the outcomes are compared against standard benchmark metrics. The proposed TFA-U-Net model demonstrates superior performance compared to several recent state-of-the-art water-body segmentation models. Experimental results show that the proposed model achieves a precision of 0.94, sensitivity of 0.96, Dice score of 0.93, accuracy of 0.97, and mean IoU of 0.85, indicating its effectiveness for accurate water-body segmentation using low-resolution satellite images.