Search Results (1,515)

Rubber–textile conveyor belts are an important element of large-scale transport systems, which in many cases are subjected to excessive dynamic loads. Assessing the impact resistance of them is essential for ensuring their reliability and longevity. The article focuses on the use of machine learning methods as one of the approaches to the analysis and prediction of the impact resistance of rubber–textile conveyor belts. Based on the data obtained from the design properties of conveyor belts and experimental testing conditions, four models were created (regression model, decision tree regression model, random forest model, ANN model), which are used to analyze and predict the impact force of the force acting on the conveyor belt during material impact. Each model was trained on training data and validated on test data. The performance of each model was evaluated using standard metrics and model indicators. The results of the model analysis show that the most powerful model, ANN, explains up to 99.6% of the data variability. The second-best model is the random forest model and then the regression model. The least suitable choice for predicting the impact force is the regression tree. Full article

Background/Objectives: Melanoma is an aggressive type of skin cancer that poses serious health risks if not detected in its early stages. Although early diagnosis enables effective treatment, delays can result in life-threatening consequences. Traditional diagnostic processes predominantly rely on the subjective expertise of dermatologists, which can lead to variability and time inefficiencies. Consequently, there is an increasing demand for automated systems that can accurately classify melanoma lesions and retrieve visually similar cases to support clinical decision-making. Methods: This study proposes a transfer learning (TL)-based deep learning (DL) framework for the classification of melanoma images and the enhancement of content-based image retrieval (CBIR) systems. Pre-trained models including DenseNet121, InceptionV3, Vision Transformer (ViT), and Xception were employed to extract deep feature representations. These features were integrated using a weighted fusion strategy and classified through an Ensemble learning approach designed to capitalize on the complementary strengths of the individual models. The performance of the proposed system was evaluated using classification accuracy and mean Average Precision (mAP) metrics. Results: Experimental evaluations demonstrated that the proposed Ensemble model significantly outperformed each standalone model in both classification and retrieval tasks. The Ensemble approach achieved a classification accuracy of 95.25%. In the CBIR task, the system attained a mean Average Precision (mAP) score of 0.9538, indicating high retrieval effectiveness. The performance gains were attributed to the synergistic integration of features from diverse model architectures through the ensemble and fusion strategies. Conclusions: The findings underscore the effectiveness of TL-based DL models in automating melanoma image classification and enhancing CBIR systems. The integration of deep features from multiple pre-trained models using an Ensemble approach not only improved accuracy but also demonstrated robustness in feature generalization. This approach holds promise for integration into clinical workflows, offering improved diagnostic accuracy and efficiency in the early detection of melanoma. Full article

In the context of Industry 4.0, user demands for industrial robots have shifted toward diversification and experience-orientation. Effectively integrating users’ affective imagery requirements into industrial-robot form design remains a critical challenge. Traditional methods rely heavily on designers’ subjective judgments and lack objective data on user cognition. To address these limitations, this study develops a comprehensive methodology grounded in Kansei engineering that combines Extenics-based semantic analysis, eye-tracking experiments, and user imagery evaluation. First, we used web crawlers to harvest user-generated descriptors for industrial floor-cleaning robots and applied Extenics theory to quantify and filter key perceptual imagery features. Second, eye-tracking experiments captured users’ visual-attention patterns during robot observation, allowing us to identify pivotal design elements and assemble a sample repository. Finally, the semantic differential method collected users’ evaluations of these design elements, and correlation analysis mapped emotional needs onto stylistic features. Our findings reveal strong positive correlations between four core imagery preferences—“dignified,” “technological,” “agile,” and “minimalist”—and their corresponding styling elements. By integrating qualitative semantic data with quantitative eye-tracking metrics, this research provides a scientific foundation and novel insights for emotion-driven design in industrial floor-cleaning robots. Full article

Tapered roller bearings are extensively utilized in the aerospace industry owing to their superior load-carrying capacity and extended service life. However, the majority of research conducted by scholars on the subject of bearing lubrication has focused on ball and cylindrical roller bearings. There is a paucity of research on the internal lubricants and air distribution of tapered roller bearings under oil jet lubrication conditions. This paper presents a computational fluid dynamics (CFD) simulation model specifically designed for the oil jet lubrication of tapered roller bearings. The flow field inside the bearing cavity is analyzed under various operating conditions, and the impact of different parameters on lubrication performance is quantitatively assessed using the oil return efficiency as a metric. Additionally, an experimental test stand for the jet lubrication of tapered roller bearings was developed. The simulated oil return efficiency was compared with experimental data, revealing discrepancies within 10%, thereby validating the accuracy of the CFD model. The findings suggest that directing the oil jet toward the smaller end of the bearing, appropriately increasing the nozzle flow rate, and utilizing positive jetting can significantly improve the lubrication performance of tapered roller bearings. Full article

Structural cracks significantly threaten the safety and longevity of historical buildings, which are essential parts of cultural heritage. Conventional inspection techniques, which depend heavily on manual visual evaluations, tend to be inefficient and subjective. This research introduces an automated framework for crack and damage detection using advanced YOLO (You Only Look Once) models, aiming to improve both the accuracy and efficiency of monitoring heritage structures. A dataset comprising 2500 high-resolution images was gathered from historical buildings and categorized into four levels of damage: no damage, minor, moderate, and severe. Following preprocessing and data augmentation, a total of 5000 labeled images were utilized to train and evaluate four YOLO variants: YOLOv5, YOLOv8, YOLOv10, and YOLOv11. The models’ performances were measured using metrics such as precision, recall, mAP@50, mAP@50–95, as well as losses related to bounding box regression, classification, and distribution. Experimental findings reveal that YOLOv10 surpasses other models in multi-target detection and identifying minor damage, achieving higher localization accuracy and faster inference speeds. YOLOv8 and YOLOv11 demonstrate consistent performance and strong adaptability, whereas YOLOv5 converges rapidly but shows weaker validation results. Further testing confirms YOLOv10’s effectiveness across different structural components, including walls, beams, and ceilings. This study highlights the practicality of deep learning-based crack detection methods for preserving building heritage. Future advancements could include combining semantic segmentation networks (e.g., U-Net) with attention mechanisms to further refine detection accuracy in complex scenarios. Full article

Cold-water immersion (CWI), as a common recovery method, has been widely used in the field of post-exercise fatigue recovery. However, there is still a lack of comprehensive and systematic scientific evaluation of the combined effects of cold-water immersion combined with other therapies (CWI + Other). The aim of this study was to compare the effects of CWI and CWI + Other in post-exercise fatigue recovery and to explore the potential benefits of CWI + Other. We systematically searched PubMed, Embase, Web of Science, Cochrane Library and EBSCO databases to include 24 studies (475 subjects in total) and performed a meta-analysis using standardized mean difference (SMD) and 95% confidence intervals (CIs). The results showed that both CWI + Other (SMD = −0.68, 95% CI: −1.03 to −0.33) and CWI (SMD = −0.37, 95% CI: −0.65 to −0.10) were effective in reducing delayed-onset muscle soreness (DOMS). In subgroup analyses of athletes, both CWI + Other (SMD = −1.13, 95% CI: −1.76 to −0.49) and CWI (SMD = −0.47, 95% CI: −0.87 to −0.08) also demonstrated significant effects. In addition, CWI + Other significantly reduced post-exercise C-reactive protein (CRP) levels (SMD = −0.62, 95% CI: −1.12 to −0.13), and CWI with water temperatures higher than 10 °C also showed a CRP-lowering effect (MD = −0.18, 95% CI: −0.30 to −0.07), suggesting a potential benefit in anti-inflammation. There were no significant differences between the two interventions in the metrics of creatine kinase (CK; CWI: SMD = −0.01, 95% CI: −0.27 to 0.24; CWI + Other: SMD = 0.26, 95% CI: −0.51 to 1.03) or countermovement jump (CMJ; CWI: SMD = 0.22, 95% CI: −0.13 to 0.57; CWI + Other: SMD = 0.07, 95% CI: −0.70 to 0.85). Full article

This research introduces an automated 3D virtual reconstruction system tailored for architectural heritage (AH) applications, contributing to the ongoing paradigm shift from traditional CAD-based workflows to artificial intelligence-driven methodologies. It reviews recent advancements in machine learning and deep learning—particularly neural radiance fields (NeRFs) and its successor, Gaussian splatting (GS)—as state-of-the-art techniques in the domain. The study advocates for replacing point cloud data in heritage building information modeling workflows with image-based inputs, proposing a novel “photo-to-BIM” pipeline. A proof-of-concept system is presented, capable of processing photographs or video footage of ancient ruins—specifically, Romanesque–Mudéjar churches—to automatically generate 3D mesh reconstructions. The system’s performance is assessed using both objective metrics and subjective evaluations of mesh quality. The results confirm the feasibility and promise of image-based reconstruction as a viable alternative to conventional methods. The study successfully developed a system for automated 3D mesh reconstruction of AH from images. It applied GS and Mip-splatting for NeRFs, proving superior in noise reduction for subsequent mesh extraction via surface-aligned Gaussian splatting for efficient 3D mesh reconstruction. This photo-to-mesh pipeline signifies a viable step towards HBIM. Full article

Background: The rising demand for aesthetic dental treatments has spurred interest in peroxide-free color correctors as alternatives to traditional hydrogen peroxide formulations, which are associated with tooth sensitivity and potential enamel demineralization. This systematic review evaluates the whitening efficacy and safety profile of hydrogen peroxide-free color corrector (HPFCC) products, focusing on color change metrics, enamel and dentin integrity, and adverse effects. Methods: Following PRISMA guidelines, we searched PubMed, Scopus, and Web of Science throughout January 2025 for randomized controlled trials, observational studies, and in vitro experiments comparing HPFCC to placebo or peroxide-based agents. The data extraction covered study design, sample characteristics, intervention details, shade improvement (ΔE00 or CIE Lab), enamel/dentin mechanical properties (microhardness, roughness, elastic modulus), and incidence of sensitivity or tissue irritation. Risk of bias was assessed using the Cochrane tool for clinical studies and the QUIN tool for in vitro research. Results: Six studies (n = 20–80 samples or subjects) met the inclusion criteria. In vitro, HPFCC achieved mean ΔE00 values of 3.5 (bovine incisors; n = 80) and 2.8 (human molars; n = 20), versus up to 8.9 for carbamide peroxide (p < 0.01). Across studies, HPFCC achieved a mean ΔE00 of 2.8–3.5 surpassing the perceptibility threshold of 2.7 and approaching the clinical acceptability benchmark of 3.3. Surface microhardness increased by 12.9 ± 11.7 VHN with HPFCC (p < 0.001), and ultramicrohardness rose by 110 VHN over 56 days in prolonged use studies. No significant enamel erosion or dentin roughness changes were observed, and the sensitivity incidence remained below 3%. Conclusions: These findings derive from one clinical trial (n = 60) and five in vitro studies (n = 20–80), encompassing violet-pigment serums and gels with differing concentrations. Due to heterogeneity in designs, formulations, and outcome measures, we conducted a narrative synthesis rather than a meta-analysis. Although HPFCC ΔE00 values were lower than those of carbamide peroxide, they consistently exceeded perceptibility thresholds while maintaining enamel integrity and causing sensitivity in fewer than 3% of subjects, supporting HPFCCs as moderate but safe alternatives for young patients. Full article

Jute, a vital lignocellulosic fiber crop with substantial industrial and ecological relevance, continues to suffer considerable yield and quality degradation due to pervasive foliar pathologies. Traditional diagnostic modalities reliant on manual field inspections are inherently constrained by subjectivity, diagnostic latency, and inadequate scalability across geographically distributed agrarian systems. To transcend these limitations, we propose DERIENet, a robust and scalable classification approach within a deep ensemble learning framework. It is meticulously engineered by integrating three high-performing convolutional neural networks—ResNet50, InceptionV3, and EfficientNetB0—along with regularization, batch normalization, and dropout strategies, to accurately classify jute leaf diseases such as Cercospora Leaf Spot, Golden Mosaic Virus, and healthy leaves. A key methodological contribution is the design of a novel augmentation pipeline, termed Geometric Localized Occlusion and Adaptive Rescaling (GLOAR), which dynamically modulates photometric and geometric distortions based on image entropy and luminance to synthetically upscale a limited dataset (920 images) into a significantly enriched and diverse dataset of 7800 samples, thereby mitigating overfitting and enhancing domain generalizability. Empirical evaluation, utilizing a comprehensive set of performance metrics—accuracy, precision, recall, F1-score, confusion matrices, and ROC curves—demonstrates that DERIENet achieves a state-of-the-art classification accuracy of 99.89%, with macro-averaged and weighted average precision, recall, and F1-score uniformly at 99.89%, and an AUC of 1.0 across all disease categories. The reliability of the model is validated by the confusion matrix, which shows that 899 out of 900 test images were correctly identified and that there was only one misclassification. Comparative evaluations of the various ensemble baselines, such as DenseNet201, MobileNetV2, and VGG16, and individual base learners demonstrate that DERIENet performs noticeably superior to all baseline models. It provides a highly interpretable, deployment-ready, and computationally efficient architecture that is ideal for integrating into edge or mobile platforms to facilitate in situ, real-time disease diagnostics in precision agriculture. Full article

Acoustic quality is one of the aspects that contribute to the heritage of cultural and religious spaces. It is increasingly common to find scientific literature detailing the sound characteristics of places of worship, especially those with cultural and historical significance. This article presents a comprehensive acoustic characterization of three colonial heritage churches in Quito. It examines the relationship between objective and subjective parameters that influence the valuation of a space or sound environment. To analyze this relationship, we employed structural equation modeling (SEM) to evaluate three latent variables using perceptual acoustic indicators. The SEM results highlighted significant associations between physical acoustic parameters, emotional responses, and evaluative judgments, underscoring that traditional intelligibility metrics alone may not fully capture acoustic quality in these contexts. These findings provide a robust interdisciplinary framework that spans objective measures and human perception, offering valuable guidance for future heritage conservation efforts. Full article

Deep learning-based super-resolution (SR) frameworks are widely used in remote sensing applications. However, existing SR models still face limitations, particularly in recovering contours, fine features, and textures, as well as in effectively integrating channel information. To address these challenges, this study introduces a novel residual model named OARN (Optimized Attention Residual Network) specifically designed to enhance the visual quality of low-resolution images. The network operates on the Y channel of the YCbCr color space and integrates LKA (Large Kernel Attention) and OCM (Optimized Convolutional Module) blocks. These components can restore large-scale spatial relationships and refine textures and contours, improving feature reconstruction without significantly increasing computational complexity. The performance of OARN was evaluated using satellite images from WorldView-2, GaoFen-2, and Microsoft Virtual Earth. Evaluation was conducted using objective quality metrics, such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Edge Preservation Index (EPI), and Perceptual Image Patch Similarity (LPIPS), demonstrating superior results compared to state-of-the-art methods in both objective measurements and subjective visual perception. Moreover, OARN achieves this performance while maintaining computational efficiency, offering a balanced trade-off between processing time and reconstruction quality. Full article

The present study explores the use of Instagram as an innovative strategy in the teaching–learning process in the context of animal reproduction topics. In the current era, with digital technology and social media transforming how information is accessed and consumed, it is essential for teachers to adapt and harness the potential of these tools for educational purposes. This article delves into the need for teachers to stay updated with current trends and the importance of promoting digital competences among teachers. This research aims to provide insights into the benefits of integrating social media into the educational landscape. Students of Veterinary Science degrees, Master’s degrees in Equine Sport Medicine as well as vocational education and training (VET) were involved in this study. An Instagram account named “UCOREPRO” was created for educational use, and it was openly available to all users. Instagram usage metrics were consistently tracked. A voluntary survey comprising 35 questions was conducted to collect feedback regarding the educational use of smartphone technology, social media habits and the UCOREPRO Instagram account. The integration of Instagram as an educational tool was positively received by veterinary students. Survey data revealed that 92.3% of respondents found the content engaging, with 79.5% reporting improved understanding of the subject and 71.8% acquiring new knowledge. Students suggested improvements such as more frequent posting and inclusion of academic incentives. Concerns about privacy and digital distraction were present but did not outweigh the perceived benefits. The use of short videos and microlearning strategies proved particularly effective in capturing students’ attention. Overall, Instagram was found to be a promising platform to enhance motivation, engagement, and informal learning in veterinary education, provided that thoughtful integration and clear educational objectives are maintained. In general, students expressed positive opinions about the initiative, and suggested some ways in which it could be improved as an educational tool. Full article

Investigating brain area functions requires advanced technologies, but meaningful insights depend on correlating neural signals with behavior. Traditional mice behavior annotation methods, including manual and semi-automated approaches, are limited by subjectivity and time constraints. To overcome these limitations, our study employs the YOLO neural network for precise mice tracking and composite RGB frames for behavioral scoring. Our model, trained on over 10,000 frames, accurately classifies sitting, running, and grooming behaviors. Additionally, we provide statistical metrics and data visualization tools. We further combined AI-powered behavior labeling to examine hippocampal neuronal activity using fluorescence microscopy. To analyze neuronal circuit dynamics, we utilized a manifold analysis approach, revealing distinct functional patterns corresponding to transgenic 5xFAD Alzheimer’s model mice. This open-source software enhances the accuracy and efficiency of behavioral and neural data interpretation, advancing neuroscience research. Full article

Virtual reality (VR) can enrich neuropsychological testing, yet the ergonomic trade-offs of its input modes remain under-examined. Seventy-seven healthy volunteers—young (19–29 y) and middle-aged (35–56 y)—completed a VR Trail Making Test with three pointing methods: eye-tracking, head-gaze, and a six-degree-of-freedom hand controller. Completion time, spatial accuracy, and error counts for the simple (Trail A) and alternating (Trail B) sequences were analysed in 3 × 2 × 2 mixed-model ANOVAs; post-trial scales captured usability (SUS), user experience (UEQ-S), and acceptability. Age dominated behaviour: younger adults were reliably faster, more precise, and less error-prone. Against this backdrop, input modality mattered. Eye-tracking yielded the best spatial accuracy and shortened Trail A time relative to manual control; head-gaze matched eye-tracking on Trail A speed and became the quickest, least error-prone option on Trail B. Controllers lagged on every metric. Subjective ratings were high across the board, with only a small usability dip in middle-aged low-gamers. Overall, gaze-based ray-casting clearly outperformed manual pointing, but optimal choice depended on task demands: eye-tracking maximised spatial precision, whereas head-gaze offered calibration-free enhanced speed and error-avoidance under heavier cognitive load. TMT-VR appears to be accurate, engaging, and ergonomically adaptable assessment, yet it requires age-specific–stratified norms. Full article

In recent years, the rapid development of lightweight Unmanned Aerial Vehicle (UAV) technology under 250 g has begun to challenge the validity of existing mass-based safety classifications. The commonly used 250 g threshold for defining “harmless” UAVs has become a subject requiring more detailed evaluations, especially as new models with increased speed and performance enter the market. This study aims to reassess the adequacy of the current 250 g mass limit by conducting a comprehensive analysis using human-centered injury metrics, including kinetic energy, Blunt Criterion (BC), Viscous Criterion (VC), and the Abbreviated Injury Scale (AIS). Within this scope, an extensive dataset of commercial UAV models under 500 g was compiled, with a particular focus on the sub-250 g segment. For each model, KE, BC, VC, and AIS values were calculated using publicly available technical data and validated physical models. The results were compared against established injury thresholds, such as 14.9 J (AIS-3 serious injury), 25 J (“harmless” threshold), and 33.9 J (AIS-4 severe injury). Furthermore, new recommendations were developed for regulatory authorities, including energy-based classification systems and mission-specific dynamic threshold mechanisms. According to the findings of this study, most UAVs under 250 g continue to remain below the current “harmless” threshold values. However, some next-generation high-speed UAV models are approaching or exceeding critical KE levels, indicating a need to reassess existing regulatory approaches. Additionally, the strong correlation between both BC and VC metrics with AIS outcomes demonstrates that these indicators are complementary and valuable tools for assessing injury risk. In this context, the adoption of an energy-based supplementary classification and dynamic, mission-based regulatory frameworks is recommended. Full article