Results in Engineering最新文献

{"title":"Impact of thermal radiation and magnetohydrodynamics on hybrid nanofluid flow over a vertical plate","authors":"Manimegalai C., Peri K. Kameswaran","doi":"10.1016/j.rineng.2025.106969","DOIUrl":"10.1016/j.rineng.2025.106969","url":null,"abstract":"<div><div>Recent technological developments have concentrated on the application of nanotechnology and solar-based heat radiation. Solar energy is the primary source of heat and is acquired by absorbing sunlight. Therefore, the main concern of this study is to explore the combined effect of buoyancy-driven hybrid nanofluid flow and the impact of the magnetic field and radiation on the non-Darcy porous medium. The purpose of hybrid nanofluids used in this study is to raise the heat transfer rate, reduce radiation loss, and produce high thermal efficiency in solar collectors. The main features of this research are the improved thermal conductivity of the working fluid in the solar collector. The <span><math><mi>A</mi><msub><mrow><mi>l</mi></mrow><mrow><mn>2</mn></mrow></msub><msub><mrow><mi>O</mi></mrow><mrow><mn>3</mn></mrow></msub><mo>−</mo><mi>C</mi><mi>u</mi><mi>O</mi><mo>/</mo><msub><mrow><mi>H</mi></mrow><mrow><mn>2</mn></mrow></msub><mi>O</mi></math></span> and <span><math><mi>A</mi><mi>g</mi><mo>−</mo><mi>C</mi><mi>u</mi><mo>/</mo><msub><mrow><mi>H</mi></mrow><mrow><mn>2</mn></mrow></msub><mi>O</mi></math></span> are the hybrid nanofluids utilized in this investigation to improve the solar collector's performance. The Mathematical model described in this study consists of the Navier-Stokes equations. The magnetic field and thermal radiation are included in the momentum and energy equations. The resultant governing equations are solved numerically by MATLAB. The numerical results are validated with the existing results in the literature for a particular case, and they are in good agreement. The graphical illustration showed that with an increase in nanoparticle volume fraction, the temperature profile increases more in <span><math><mi>A</mi><mi>g</mi><mo>−</mo><mi>C</mi><mi>u</mi><mo>/</mo><msub><mrow><mi>H</mi></mrow><mrow><mn>2</mn></mrow></msub><mi>O</mi></math></span> than <span><math><mi>A</mi><msub><mrow><mi>l</mi></mrow><mrow><mn>2</mn></mrow></msub><msub><mrow><mi>O</mi></mrow><mrow><mn>3</mn></mrow></msub><mo>−</mo><mi>C</mi><mi>u</mi><mi>O</mi><mo>/</mo><msub><mrow><mi>H</mi></mrow><mrow><mn>2</mn></mrow></msub><mi>O</mi></math></span>; due to this, the heat transfer rate is low in solar collectors. The developed data-driven model resulted in that for 10% nanoparticle volume fraction <span><math><mi>A</mi><mi>g</mi><mo>−</mo><mi>C</mi><mi>u</mi><mo>/</mo><msub><mrow><mi>H</mi></mrow><mrow><mn>2</mn></mrow></msub><mi>O</mi></math></span> and <span><math><mi>A</mi><msub><mrow><mi>l</mi></mrow><mrow><mn>2</mn></mrow></msub><msub><mrow><mi>O</mi></mrow><mrow><mn>3</mn></mrow></msub><mo>−</mo><mi>C</mi><mi>u</mi><mi>O</mi><mo>/</mo><msub><mrow><mi>H</mi></mrow><mrow><mn>2</mn></mrow></msub><mi>O</mi></math></span> achieving 72.55% and 68.71% heat transfer rate. This study finds that as the magnetic parameter increases, there is a reduction in fluid velocity and an increase in temperature. As the Hartman number increases to the range 2, ","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 106969"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A process intensification approach for industrial plant decarbonization: Scale-up, techno-economic, and environmental assessment","authors":"Mohammad Shamsi ,&nbsp;Jafar Towfighi Darian ,&nbsp;Morteza Afkhamipour","doi":"10.1016/j.rineng.2025.107153","DOIUrl":"10.1016/j.rineng.2025.107153","url":null,"abstract":"<div><div>Given the diverse sources of CO₂ emissions, selecting an efficient and cost-effective carbon capture technology is crucial. Although RPB absorbers serve as a potential replacement for traditional packed columns, scaling them up to an industrial level presents a challenge. This research outlines the design and provides a techno-economic, and environmental assessment of an industrial-scale carbon capture process utilizing a DETA solution. The RPB absorber was designed using an iterative methodology for carbon capture retrofitting in an existing petrochemical plant. A carbon-techno-economic analysis approach was developed to integrate process costs and carbon tax into a unified metric for simultaneously evaluating economic and environmental impacts. In the design of the RPB for the flue gas from the fired heater, the optimal liquid-to-gas ratio was determined. After designing the RPB, the variations in loading, CO₂ mole fraction, temperature, CO₂ capture level, and the concentration of molecular and ionic species in the liquid phase were evaluated in an industrial-scale setting using a steady-state rate-based model along the radial direction. The impact of operating parameters, such as liquid temperature, rotation speed, and solvent concentration, as well as their optimal values, on the total annual cost for minimizing CO₂ avoidance costs, were examined. Cash flow analysis showed that the implementation of carbon capture technology resulted in a net carbon tax avoided of 2771 k$/yr and a CO₂ capture cost of $12.3/t_CO2, indicating the cost-effectiveness of using intensified process technology to address environmental concerns and reduce the process equipment footprint.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107153"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TEA-Watershed:A temporal-enhanced adaptive watershed framework for real-time particle size measurement in dynamic industrial flows","authors":"Fusheng Niu ,&nbsp;Zhiheng Nie ,&nbsp;Jinxia Zhang ,&nbsp;Yaowen Xing ,&nbsp;Xinwei Wang ,&nbsp;Yanpeng Wang ,&nbsp;Jianfeng Shi ,&nbsp;Jiahui Wu","doi":"10.1016/j.rineng.2025.107173","DOIUrl":"10.1016/j.rineng.2025.107173","url":null,"abstract":"<div><div>Accurate real-time particle-size measurement in rapid, illumination-varying industrial flows is hindered by motion blur, inter-particle adhesion, and uneven grayscale distributions. This study introduces TEA-Watershed (Temporal-Enhanced Adaptive Watershed), a training-free framework that delivers robust in-line metrology without interrupting production. The algorithm fuses consecutive frames to reinforce edges, integrates motion-aware parameter optimization with adaptive Otsu thresholding inside a watershed pipeline, and iteratively refines segmentation through trajectory-based feedback. An unsupervised K-Means module further groups particles by morphology, eliminating manual annotation while maintaining calibration under changing flow conditions. Validation on 2–15 mm coal and iron-ore streams achieved a mean Intersection-over-Union of 89.1 % and pixel accuracy of 96.2 %. For metrological performance, the system recorded a mean absolute size error of 3.8 % and a repeatability coefficient of variation below 2.5 % across 100 replicates. Processing throughput reached 22 frames s⁻¹(45 ms per frame), enabling continuous monitoring. Correlation with ISO 2591 sieve analysis confirmed high reliability (R² = 0.98). Requiring only modest computational resources and no learned weights, TEA-Watershed provides quantified uncertainty within industrial tolerances, offering a practical, scalable solution for particle-size measurement, screening-efficiency assessment, and flow diagnostics in mineral processing, coal beneficiation, and powder-handling operations.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107173"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Minimizing vibrations and power consumption in milling of AZ31 alloy through parameter optimization","authors":"Muhammad Atif Saeed","doi":"10.1016/j.rineng.2025.107186","DOIUrl":"10.1016/j.rineng.2025.107186","url":null,"abstract":"<div><div>This study presents an integrated optimization framework for minimizing vibration and power consumption during the milling of AZ31 magnesium alloy. A total of 25 experiments were performed using a Taguchi L₂₅ orthogonal array to investigate the influence of spindle speed, feed rate, and depth of cut. Real-time data acquisition captured vibrations along the X, Y, and Z axes, as well as power consumption. Stepwise regression models were developed using Pearson’s correlation analysis, revealing spindle speed as the most influential parameter. These models were input into the NSGA-II algorithm, generating a Pareto front of optimal solutions. The best theoretical solution predicted vibration amplitudes of −8.2 mm (X), 7.7 mm (Y), 4.2 mm (Z), and a power consumption of 68.13 W. Experimental validation yielded errors of 4 % (X), 4 % (Y), 10 % (Z), and −6 % (power), confirming the model's accuracy. Correlation analysis indicated that spindle speed had the greatest influence on power consumption and Z-axis vibrations (<em>r</em> = 0.45 and <em>r</em> = 0.16), depth of cut significantly affected X-axis and Y-axis vibrations (<em>r</em> = 0.27 and <em>r</em> = 0.15) The framework effectively improves machining sustainability by optimizing process parameters.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107186"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Flexible and eco-friendly piezoelectric nanogenerator based on PVDF-HFP: CBT: Ag fibers for self-powered sensing applications","authors":"R. Gowdaman,&nbsp;A. Deepa","doi":"10.1016/j.rineng.2025.107184","DOIUrl":"10.1016/j.rineng.2025.107184","url":null,"abstract":"<div><div>In this study, we developed an eco-friendly and adaptable piezoelectric nanogenerator (PENG) using a composite material composed of copper-doped barium titanate (CBT) and silver (Ag) nanoparticles, combined with poly (vinylidene fluoride-co-hexafluoropropylene) (PVDF-HFP). X-ray diffraction (XRD) confirmed the successful incorporation of CBT-Ag into the polymer matrix, and FTIR results showed an enhancement of the β-phase in the nanocomposite film. FESEM imaging demonstrated consistent dispersion of the nanofillers and a smooth, defect-free nanofiber structure. Tensile and thermal studies demonstrated the composite film's good elongation and heat-resistance properties. The constructed PENG devices were subjected to mechanical stimulation using an electrometer. Nanocomposite films containing 5 wt% CBT-Ag exhibited superior piezoelectric performance, producing an open-circuit voltage of 6.5 V and a current of 1.1 µA. This study proposes a feasible platform to eliminate the need for an external power source in the operation of portable devices. Consequently, the developed PENG exhibits significant potential and can act as an effective alternative to conventional power sources in self-sustaining devices, thereby ensuring its durability and adaptability.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107184"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bridge damage characterisation using machine learning: methods and advances","authors":"Francesco Pentassuglia ,&nbsp;Ivan Izonin ,&nbsp;Stergios-Aristoteles Mitoulis","doi":"10.1016/j.rineng.2025.107192","DOIUrl":"10.1016/j.rineng.2025.107192","url":null,"abstract":"<div><div>Bridge deflection is a descriptive proxy for potential bridge deterioration and damage. It can be used to determine bridge condition and link this to actionable damage states for timely and accurate damage mitigation and adaptation. While design guidelines mandate strict deflection control at the design stage, primarily for serviceability, there are currently no assessment guidelines or available framework to facilitate bridge damage identification based on bridge deck deflections. A thorough review of the literature revealed that the main reason that deflection is not used as a damage proxy is the complex mechanics underlying its development. A state-of-the-art review is presented to efficiently characterise global bridge damage related to deck deflections. The approach goes beyond existing methods by striving to reveal the causes of bridge deck deflection and their interdependencies, offering a clearer understanding and interpretation of the factors driving this phenomenon. Given the significant uncertainties around deflection causes and the impracticality of complex, tedious analyses for large bridge portfolios, Machine Learning (ML) is proposed as a scalable solution that reduces modelling effort, enhances explainability, and can successfully correlate deflections with damage levels. It then proposes a conceptual Physics-Based ML approach that correlates deflection patterns with actionable damage states, offering a roadmap for future research to enhance bridge damage characterisation. Unlike prior studies, it integrates all major deterioration mechanisms and their interactions into a unified deflection analysis.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107192"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating the effect of the atomic ratio of ClO2 Gas on the disinfection process of the influenza virus using molecular dynamics simulation","authors":"Narinderjit Singh Sawaran Singh ,&nbsp;Ibrahim Saeed Gataa ,&nbsp;Imad S. aboud ,&nbsp;Sarhang Hayyas Mohammed ,&nbsp;Soheil Salahshour ,&nbsp;S. Mohammad Sajadi ,&nbsp;Hani Sahramaneshi","doi":"10.1016/j.rineng.2025.107175","DOIUrl":"10.1016/j.rineng.2025.107175","url":null,"abstract":"<div><div>Influenza virus transmission remains a critical public health concern, necessitating effective disinfection strategies to control outbreaks. However, the molecular mechanisms by which varying atomic ratios of chlorine dioxide (ClO₂) gas affect viral destabilization and inactivation are not fully understood. To address this knowledge gap, this study used molecular dynamics simulations using the LAMMPS software to investigate interactions between ClO₂ gas and the influenza virus at different atomic ratios. Increasing the ClO₂ concentration from 15 % to 50 % significantly raised virus-gas interaction energy from 25,377.83 kcal/mol to 83,430.95 kcal/mol and virus-virus interaction energy from 523,570.84 kcal/mol to 558,130.12 kcal/mol. Concurrently, mean square displacement decreased, indicating reduced viral atom mobility, and the radius of gyration contracted from 68.55 Å to 65.58 Å, reflecting structural collapse. These molecular-level findings demonstrate that higher ClO₂ atomic ratios strengthened the interactions that led to viral destabilization and accelerated structural breakdown, providing quantitative insights to optimize ClO₂ dosing protocols for effective disinfection in healthcare and public environments. Moreover, the results can inform the development of advanced antiviral surface treatments and air purification technologies.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107175"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating the protection motivation model with place attachment theory to examine rural residents’ intentions toward low-carbon behaviors: Empirical evidence from Iran","authors":"Ali Mokhtari Karchegani ,&nbsp;Moslem Savari","doi":"10.1016/j.rineng.2025.107180","DOIUrl":"10.1016/j.rineng.2025.107180","url":null,"abstract":"<div><div>The continuous rise in carbon emissions has intensified climate change, generating widespread concern across all sectors of society. Although rural areas are typically regarded as less industrialized, they contribute substantially to carbon emissions through traditional practices such as deforestation and biomass burning. Existing research identifies Protection Motivation Theory (PMT) as one of the predominant frameworks for understanding low-carbon behavior. However, PMT does not account for the significance of individuals’ emotional ties to place, conceptualized by Place Attachment Theory (PAT), which can provide critical insights into the behavioral intentions of rural populations. To address this gap, the study aimed to develop an extended PMT model incorporating PAT as an additional construct. This research employed a questionnaire survey and utilized structural equation modeling (SEM) for analysis. The study targeted all villagers in Sistan and Baluchestan province, Iran. Following the Krejcie and Morgan (1970) sampling table, a sample of 383 individuals was selected through a multistage stratified cluster sampling method. Data analysis was conducted using the PLS-SEM approach. The findings revealed that the original PMT model accounted for only 59.9 % of the variance in villagers’ intentions to engage in low-carbon behaviors, whereas the extended PMT model, incorporating PAT, enhanced the explanatory power by an additional 27.7 %. The theoretical framework established in this study offers a valuable reference for future investigations into the low-carbon behavioral intentions of rural populations. Moreover, the insights gained can assist policymakers in designing effective conservation policies that align with local community values while safeguarding environmental and social well-being.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107180"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing drug recovery efficiency: A numerical solution approach with electromembrane extraction modeling","authors":"Fatemeh Mansouri,&nbsp;Ahmad Rahbar-kelishami","doi":"10.1016/j.rineng.2025.107177","DOIUrl":"10.1016/j.rineng.2025.107177","url":null,"abstract":"<div><div>Electromembrane extraction (EME) has gained attention as an efficient alternative to conventional sample preparation, yet the mechanistic understanding of coupled electrokinetic and mass transport phenomena remains limited. To address this gap, we developed a numerical framework based on the coupled Poisson–Nernst–Planck equations, solved via the finite element method in COMSOL Multiphysics, to investigate the extraction of basic and acidic drugs under realistic partitioning conditions. A comprehensive parametric study was conducted, examining the effects of applied voltage, donor/acceptor phase pH, membrane thickness, drug diffusivity, porosity, initial concentration, and extraction time. The results revealed a strong correlation between flux and potential difference across the supported liquid membrane: extraction recovery increased from 46 % to nearly 100 % when the voltage was raised from 5 to 30 V. Moreover, a maximum recovery of 97.6 % was achieved at a donor phase pH of 2. Sensitivity to membrane thickness and drug diffusivity was also confirmed, highlighting the importance of partitioning effects on extraction performance. These findings provide mechanistic insights and practical guidelines for optimizing EME, with direct relevance to pharmaceutical separations and environmentally sustainable drug recovery. Beyond advancing fundamental understanding, these insights can support the design of more sustainable and efficient pharmaceutical separation processes, thereby facilitating both research development and potential industrial applications in drug recovery and purification.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107177"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic visual lip reading: A comparative review of machine-learning approaches","authors":"Khosro Rezaee ,&nbsp;Maryam Yeganeh","doi":"10.1016/j.rineng.2025.107171","DOIUrl":"10.1016/j.rineng.2025.107171","url":null,"abstract":"<div><div>Automatic lip-reading systems are evolving from traditional handcrafted pipelines to advanced deep and hybrid architectures that integrate local motion modeling with long-range temporal context. This review provides a comprehensive synthesis of classical techniques and state-of-the-art learning approaches, with a specific focus on hybrid three-dimensional convolution plus Transformer or Conformer backbones and on multimodal training strategies that enable visual-only inference. Unlike previous surveys, we critically appraise datasets through the lenses of diversity, realism, robustness, and efficiency, and we foreground responsible deployment by addressing privacy, fairness, and transparency. We propose a clear taxonomy that spans classical, hybrid, and Transformer-based models. We compare their strengths and limitations for both word- and sentence-level recognition, and analyze the trade-offs between accuracy, computational cost, latency, and interpretability. The evidence indicates that lightweight hybrid models offer high accuracy with practical efficiency and that audio-as-teacher training significantly improves visual reliability when audio is unavailable. However, progress remains constrained by limited demographic and linguistic coverage, a reliance on studio-style capture, and uneven robustness to real-world challenges like pose, illumination, motion blur, and occlusion. The review concludes with a focused call to action: we must build multilingual and demographically balanced corpora with standardized robustness testing; develop parameter-efficient hybrid backbones suitable for edge deployment; adopt self-supervised and semi-supervised learning to reduce annotation demands; and report calibrated uncertainty, fairness diagnostics, and transparent documentation. These recommendations are intended to guide researchers toward creating scalable, reliable, and trustworthy lip-reading systems for real-world applications.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107171"},"PeriodicalIF":7.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}