General Background: Deep image matting is a fundamental task in computer vision, enabling precise foreground extraction from complex backgrounds, with applications in augmented reality, computer graphics, and video processing. Specific Background: Despite advancements in deep learning-based methods, preserving fine details such as hair and transparency remains a challenge. Knowledge Gap: Existing approaches struggle with accuracy and efficiency, necessitating novel techniques to enhance matting precision. Aims: This study integrates deep learning with fusion techniques to improve alpha matte estimation, proposing a lightweight U-Net model incorporating color-space fusion and preprocessing. Results: Experiments using the AdobeComposition-1k

Future wireless networks will require advance physical-layer techniques to meet the requirements of Internet of Everything (IoE) applications and massive communication systems. To this end, a massive MIMO (m-MIMO) system is to date considered one of the key technologies for future wireless networks. This is due to the capability of m-MIMO to bring a significant improvement in the spectral efficiency and energy efficiency. However, designing an efficient downlink (DL) training sequence for fast channel state information (CSI) estimation, i.e., with limited coherence time, in a frequency division duplex (FDD) m-MIMO system when users exhibit different correlation patterns, i.e., span distinct channel covariance matrices, is to date ve

A substantial percentage of the world’s energy consumption (almost 40%) and carbon dioxide (CO2) emissions (around 37%) come from the construction industry, especially schools. This work presents a new hybrid artificial intelligence (AI) engineering model that aims to maximize energy performance on campuses in a holistic way. Modules for data-driven forecasting, metaheuristic optimization, and real-time adaptive control are all part of the concept. A thorough energy simulation of a university campus building is used in conjunction with the AI model to assess its performance through a co-simulation framework. Findings show that yearly peak electricity demand may be reduced by 18.7% and total site energy consumption by 22.4% when co

Catalytic reduction is considered an effective approach for the reduction of toxic organic pollutants from the environment, but finding an active catalyst is still a big challenge. Herein, Ag decorated CeO2 catalyst was synthesized through polyol reduction method and applied for catalytic reduction (conversion) of 4-nitrophenol (4-NP) to 4-aminophenol (4-AP). The Ag decorated CeO2 catalyst displayed an outstanding reduction activity with 99% conversion of 4-NP in 5 min with a 0.61 min−1 reaction rate (k). A number of structural characterization techniques were executed to investigate the influence of Ag on CeO2 and its effect on the catalytic conversion of 4-NP. The outstanding catalytic performances of the Ag-CeO2 catalyst can be assigne

The investigation of determining solutions for the Diophantine equation  over the Gaussian integer ring for the specific case of  is discussed. The discussion includes various preliminary results later used to build the resolvent theory of the Diophantine equation studied. Our findings show the existence of infinitely many solutions. Since the analytical method used here is based on simple algebraic properties, it can be easily generalized to study the behavior and the conditions for the existence of solutions to other Diophantine equations, allowing a deeper understanding, even when no general solution is known.