Engineering reports : open access最新文献

{"title":"Coupled Heat Transfer Inside a Thick-Walled Structure With an Inner Open Cavity: A Numerical Approach","authors":"Salma Parvin,&nbsp;Md. Mazidul Islam,&nbsp;A. K. Azad,&nbsp;Afroza Akter","doi":"10.1002/eng2.70314","DOIUrl":"https://doi.org/10.1002/eng2.70314","url":null,"abstract":"<p>This research presents numerical modeling by investigating the coupled heat transfer of conduction and free convection phenomena within a thick-walled square enclosure. This analysis aims to insert an open cavity barrier into the enclosure to reduce the natural convection effect and compare it with the empty enclosure. The top of the inner cavity is open and connected to the enclosed ceiling. The presence of the internal open cavity leads to alterations in convection patterns, resulting in diminished flow and the creation of a confined fluid compartment at the enclosure core. Consequently, this arrangement drops the local Nusselt number (<i>Nu</i>_{<b><i>l</i></b>}) along the hot interface boundary, reducing heat flux through the enclosure. The mathematical model is solved using the penalty approach of the Finite Element Method (FEM). The impact on thermal and flow behavior has been discussed for varying internal cavity dimensions (<i>l</i>/<i>L</i> = 0, 0.1, 0.3, 0.5), Rayleigh numbers (<i>Ra =</i> 10³, 10⁴, 10⁵, 10⁶), and a wall thickness (W = 0.05, 0.1, 0.15, 0.2). Clay brick's thermal property is used in the wall, and air is the heat transfer fluid. The numerical model was validated with a benchmark problem from the literature, accompanied by grid independence tests, demonstrating strong agreement with previously published studies. The outcomes reveal that the average Nusselt number was reduced up to 65.6% at <i>Ra</i> = 10⁶ as a result of the inclusion of an inner cavity (<i>l/L</i> = 0.5), highlighting a notable decrease in heat transfer with increasing cavity size. In addition, the average Nusselt number drops up to 31.5% at <i>Ra</i> = 10⁶ and W = 0.1. This research provides significant insights relevant to the design of energy-efficient building envelopes, drying technologies, and process industry systems, especially with the optimization of hollow masonry bricks.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70314","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144688141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing Photovoltaic Grid-Connected Power Systems Through Artificial Intelligence and Robust Nonlinear Control","authors":"Collins Ngong Sang,&nbsp;Harrison Ambe,&nbsp;Arnaud flanclair Tchouani Njomo,&nbsp;Zeric Tabekoueng Njitacke,&nbsp;Wulfran Fendzi Mbasso,&nbsp;Pradeep Jangir,&nbsp;Aseel Smerat","doi":"10.1002/eng2.70264","DOIUrl":"https://doi.org/10.1002/eng2.70264","url":null,"abstract":"<p>Photovoltaic (PV) systems are highly sensitive to stochastic environmental variations, particularly irradiance and temperature, which complicate the task of consistently operating at the maximum power point (MPP). This paper presents a novel dual-layer control strategy to optimize the performance of a single-phase grid-connected PV system. The proposed system integrates an Artificial Neural Network (ANN) model for real-time estimation of MPP voltage with a Lyapunov-stable nonlinear backstepping controller to regulate a DC-DC boost converter. To ensure seamless grid integration, a Phase-Locked Loop (PLL)-based Proportional Resonant (PR) controller and a PI regulator are implemented to maintain DC-link stability and minimize harmonic distortion. Unlike conventional ANN-MPPT approaches, the proposed method decouples MPP prediction from control regulation, allowing robust and fast dynamic response under varying climatic and load conditions. Extensive simulations in MATLAB/Simulink validate the effectiveness of the approach, demonstrating fast convergence to the MPP (within 30 ms), precise DC-link regulation, and excellent grid synchronization. Notably, the system achieves a low Total Harmonic Distortion (THD) of 0.2148%, outperforming existing benchmarks. Comparative analysis against P&amp;O and sliding mode controllers confirms the superior efficiency, robustness, and power quality of the proposed architecture, highlighting its potential for scalable deployment in real-world grid-connected PV applications.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70264","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144672701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MediaPipe-LSTM-Enhanced Framework for Real-Time Dynamic Sign Language Recognition in Inclusive Communication Systems","authors":"N. Anithadevi,&nbsp;SatheeshKumar Palanisamy,&nbsp;S. Saranya Rubini,&nbsp;Sachin Shrestha","doi":"10.1002/eng2.70142","DOIUrl":"https://doi.org/10.1002/eng2.70142","url":null,"abstract":"<p>Sign language serves as a crucial mode of communication for individuals with hearing and speech impairments. However, the lack of accessible recognition technologies continues to hinder inclusivity. This study presents an advanced vision-based dynamic sign language recognition system that addresses challenges related to gesture variability and contextual diversity. The proposed system leverages MediaPipe's landmark tracking alongside an enhanced stacked long short-term memory (LSTM) network for real-time identification of continuous gestures. Additionally, a transformer-based paraphrase module translates recognized gestures into semantically precise search queries, enabling seamless interaction with virtual personal assistants. To enhance recognition accuracy, a dedicated dataset of Indian sign language (ISL) gestures, encompassing 30 dynamic sign categories, was developed. This dataset facilitates precise tracking of hand, facial, and posture attributes. The proposed approach achieves exceptional performance, with 97% accuracy, 98.17% precision, and an F1-score of 94.88%, surpassing state-of-the-art spatiotemporal feature learning techniques. The system's scalability enables diverse applications in education, healthcare, and customer service, fostering greater accessibility for the deaf and mute communities. By integrating robust real-time gesture recognition with semantic understanding, this research establishes a new benchmark for dynamic sign language recognition, laying the groundwork for future advancements in attention mechanisms and optimized spatiotemporal learning.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70142","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Steel Pipe Retrofitting Method to Enhance the Seismic Performance of RC Column Under Combined Load","authors":"Min Sook Kim,&nbsp;Young Hak Lee","doi":"10.1002/eng2.70302","DOIUrl":"https://doi.org/10.1002/eng2.70302","url":null,"abstract":"<p>A reinforced concrete column is subjected to a combination of axial load, lateral load, and torsion during earthquake excitations. Torsion induced under combined load can result in brittle failure in these columns. This study introduces a retrofitting technique using steel pipes designed to resist combined loads. To evaluate the seismic performance of the steel pipe, four specimens were fabricated, varying the presence of axial force eccentricity and retrofitting. The experimental results demonstrated that the steel pipe retrofitting technique enhanced strength, ductility, energy dissipation, and torsional resistance compared with conventional columns. The maximum torsional moment of the retrofitted specimens increased by up to 2.36 times, the maximum load capacity increased by 2.2 times, and the energy dissipation capacity increased by 2.8 times compared with the unretrofitted specimen.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70302","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144673145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability Analysis of Electricity Grid Integrated With PV System and BESS at Distribution Level: A Case Study of Ntongwe and Gatumba Feeders at Rwanda's Electricity Network","authors":"Obed Nkuriyingoma,&nbsp;Engin Özdemir","doi":"10.1002/eng2.70307","DOIUrl":"https://doi.org/10.1002/eng2.70307","url":null,"abstract":"<p>The escalating energy demand in today's world underscores the need for a consistent and continuous power supply. There is a push towards promoting renewable energy sources to address this demand because of their positive impact on the environment and their widespread accessibility. Particularly in Rwanda, for the radial distribution network, the reliability improvement in electricity supply requires rectifications of power system infrastructure, including transmission, distribution system, and an increase in energy generation capacity. To evaluate the influence of renewable energy sources (RES) on the reliability of Rwanda's power grid, Solar Photovoltaic (PV) systems combined with Battery Energy Storage Systems (BESS) are introduced into the Gatumba and Ntongwe feeders. For the reliability enhancement of the grid to the feeders where the solar PV system and BESS are connected, protection switches are configured so that the PV systems and BESS supply the load demand in the absence of the grid, thereby increasing the generation capacity and reducing interruption frequency and duration. This study assesses how the integration of solar PV plants with BESS can improve the reliability of Rwanda's electricity grid, specifically at the Gatumba and Ntongwe feeders. Simulation results from DigSILENT and PV*SOL simulation tools showed that by integrating solar PV systems with BESS to Gatumba and Ntongwe feeders, the system reliability ameliorates by 71.6% and 95.5% for system average interruption frequency and duration, respectively.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70307","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144673144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization-Based Energy Management for Grid-Connected Photovoltaic–Battery Systems in Smart Grids Using Demand Response and Particle Swarm Optimization","authors":"Subhasis Panda,&nbsp;Pravat Kumar Rout,&nbsp;Binod Kumar Sahu,&nbsp;Wulfran Fendzi Mbasso,&nbsp;Pradeep Jangir,&nbsp;Ali Elrashidi","doi":"10.1002/eng2.70305","DOIUrl":"https://doi.org/10.1002/eng2.70305","url":null,"abstract":"<p>With rising temperatures and increasing power demands, microgrid failures have become frequent, highlighting the need for effective energy management. Microgrids, particularly those integrating renewable energy sources (RES), are gaining traction as decentralized energy solutions. Despite their potential, Photovoltaic (PV) systems face challenges due to the intermittent nature of solar energy, necessitating energy storage solutions to maintain a stable power supply. Battery energy storage systems (BESS) are critical in buffering power fluctuations and enhancing grid stability, forming PV-battery hybrid microgrids capable of operating in both grid-connected and islanded modes. This study focuses on optimizing the management of BESS within a solar-integrated microgrid over 24 h to improve energy efficiency and cost-effectiveness. Additionally, the study examines the implementation of demand response (DR) techniques, including peak clipping, valley filling, and load shifting, to further enhance grid stability and economic benefits. Using MATLAB for simulations, the study employs state flow study and linear programming methods. Results indicate that the energy management system (EMS) using particle swarm optimization (PSO) enhances the efficiency of EMS using linear programming (LP). Simulation results conducted using MATLAB R2023b indicate that PSO outperforms LP in minimizing daily electricity costs (up to 15.32% savings), stabilizing state of charge (SoC), and reducing grid power fluctuations. These findings underscore the importance of advanced EMS in enhancing microgrid efficiency, particularly under variable weather conditions. This research underscores the crucial role of energy management systems (EMS) in enhancing the reliability and sustainability of microgrids, particularly in rural and underdeveloped areas. By optimizing the charge and discharge cycles of BESS based on load requirements and implementing DR strategies, the proposed methods demonstrate substantial improvements in system performance and economic benefits.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70305","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144657590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FPGA-Based Design of Ultra-Efficient Approximate Adders for High-Fidelity Image Processing: A Logic-Optimized Approach","authors":"Ramakrishna Reddy Eamani,&nbsp;N. Vinodhkumar,&nbsp;Ambe Harrison,&nbsp;Wulfran Fendzi Mbasso","doi":"10.1002/eng2.70262","DOIUrl":"https://doi.org/10.1002/eng2.70262","url":null,"abstract":"<p>Emerging as a promising paradigm for improving energy efficiency in error-tolerant applications including image processing, neural networks, and embedded vision systems is approximative computing. Most current approximative adder designs, however, either compromise output quality or show poor trade-off between logic complexity and computational accuracy. In order to close this gap, this work suggests a family of new 1-bit approximate full adder (AFA) designs optimized with basic AND-OR gate logic. While keeping reasonable error margins for real-time image processing, these approaches decrease device footprint and power consumption. Conventional and state-of-the-art approximate adders were compared against the proposed AFAs—AFA1, AFA2, and AFA3—on metrics including logic use, propagation delay, power dissipation, and Peak Signal-to-Noise Ratio (PSNR) in picture enhancement tasks. On an Intel Cyclone IV EP4CE115 FPGA, the AFAs attained up to 45.3% decrease in LUT utilization, 29.9% reduced power consumption, and 34.1% speed improvement over traditional full adders. The best-performing design (AFA3) in image addition studies produced a PSNR of 34.6 dB, therefore verifying good perceptual integrity appropriate for use in practical vision applications. This work provides a compact, energy-efficient design framework for digital image processing systems, therefore advancing the state of approximative arithmetic. Strong prospects for deployment in low-power, resource-constrained environments including IoT edge devices, and FPGA-based accelerators are the architectural simplicity and error-resilient behavior of the suggested adders.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70262","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144657586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Risk Analysis Under Uncertainty, Subjectivity, and Incomplete Knowledge: With a Use Case of Energy System Failures","authors":"Ali Aghazadeh Ardebili,&nbsp;Mahdad Pourmadadkar,&nbsp;Elio Padoano","doi":"10.1002/eng2.70286","DOIUrl":"https://doi.org/10.1002/eng2.70286","url":null,"abstract":"<p>The reliability of gas turbines is crucial due to their critical applications in energy systems and the increasing complexity of their design and operation. Traditional failure mode and effects analysis (FMEA) methods face significant limitations in handling combined uncertainty under conditions of ambiguity and partial information. Although widely used, fuzzy variations of FMEA naturally fall short in simultaneously addressing both sources of uncertainty: Ambiguity and incomplete knowledge. This study investigates the application of fuzzy-rough FMEA (FR-FMEA) to bridge this gap. By integrating fuzzy logic with rough set theory, FR-FMEA effectively manages uncertainties arising from incomplete knowledge and vagueness in expert judgment, providing a more reliable framework for risk prioritization. A case study on a gas turbine demonstrates the application of the proposed method. The results show that FR-FMEA provides distinct and reliable rankings, reducing clustering while aligning more closely with conventional RPN rankings. Key components such as the combustion chamber, fuel nozzle, and turbine rotor were consistently identified as high-risk across methods, emphasizing their criticality for maintenance and design optimization. Moreover, the results are also compared with conventional FMEA and Fuzzy-FMEA to highlight the differences.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70286","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144657587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling the Dynamics of Fungal Diseases in Onion Cultivation With Optimal Control Strategies","authors":"Dejen Ketema Mamo,&nbsp;Mathew Ngugi Kinyanjui,&nbsp;Yohannes Fissha Abebaw,&nbsp;Gizachew Kefelew Hailu,&nbsp;Shewafera Wondimagegnhu Teklu","doi":"10.1002/eng2.70300","DOIUrl":"https://doi.org/10.1002/eng2.70300","url":null,"abstract":"<p>Onion cultivation (<i>Allium cepa</i>), a crucial crop worldwide, is threatened by fungal pathogens, leading to substantial reductions in yield and economic challenges. We present a new deterministic compartmental model to study the dynamics of fungal diseases in onion fields. Incorporating spore generation, latency phases, and control strategies such as fungicides and infected plant removal. The stability of the endemic and disease-free equilibrium, based on the basic reproduction number (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>ℛ</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>0</mn>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {mathcal{R}}_0 $$</annotation>\u0000 </semantics></math>), guides strategies to lower disease cases and reduce intervention costs. Sensitivity analysis with partial rank correlation coefficients highlights spore deposition rate (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>ν</mi>\u0000 </mrow>\u0000 <annotation>$$ nu $$</annotation>\u0000 </semantics></math>) and infection coefficients (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>β</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>1</mn>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {beta}_1 $$</annotation>\u0000 </semantics></math>, <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>β</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>2</mn>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {beta}_2 $$</annotation>\u0000 </semantics></math>) as critical factors for pathogen dissemination, with reduced fungicide effectiveness and spore decay (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>ϵ</mi>\u0000 </mrow>\u0000 <annotation>$$ epsilon $$</annotation>\u0000 </semantics></math>). Simulations revealed that combining fungicide with plant removal significantly reduces infections, providing an economical approach. The model bridges epidemiological theory with disease control, serving as a valuable resource for improving onion crop resilience and advancing sustainable farming.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70300","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144657589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"QuadWindow: A Perspective-Aware Framework for Geometric Window Extraction From Street-View Imagery","authors":"Zhuangqun Niu,&nbsp;Ke Xi,&nbsp;Yifan Liao,&nbsp;Pengjie Tao,&nbsp;Tao Ke","doi":"10.1002/eng2.70294","DOIUrl":"https://doi.org/10.1002/eng2.70294","url":null,"abstract":"<p>Rapid and reliable assessment of building damage is essential for post-disaster response and recovery. As windows often reflect critical structural changes, their automatic extraction from street-view images provides valuable insights for emergency assessment, urban risk modeling, and disaster database updates. Existing methods struggle to leverage the quadrilateral prior of windows due to two main issues: poor handling of perspective distortion and the lack of robust loss functions when precise vector annotations are unavailable. To overcome these challenges, we introduce QuadWindow, a framework specifically designed to handle perspective distortions through a perspective transformation sub-network that predicts transformations from street-view images to frontal views, significantly simplifying window extraction tasks without manual correction. Additionally, we propose a differentiable rendering loss that directly aligns predicted quadrangles with raster-based ground truth, bypassing the need for explicit corner-point annotations. Experimental results demonstrate that QuadWindow outperforms state-of-the-art methods across five façade datasets, with an average F1-score of 87.6% and Intersection over Union (IoU) of 78.03%, achieving 1.47% and 5.2% improvement, respectively.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 7","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70294","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144647119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}