Search Results (556)

This study developed a machine learning approach to detect carbide precipitation in the microstructure of austenitic stainless steel, specifically grade 316, using a convolutional neural network (CNN). Microstructural images were prepared and classified into three categories: as-received, heat-treated without carbide precipitation, and heat-treated with carbide precipitation. A CNN was trained and validated using two separate datasets of varying sizes to assess the impact of data quantity on classification performance. This automated microstructure recognition system offers potential benefits for additive manufacturing (AM) by enabling real-time quality assessment and feedback control, particularly for avoiding undesirable carbide formation during metal 3D printing. By linking microstructural analysis to processing conditions, this approach supports the development of defect-free, corrosion-resistant components and contributes to the integration of intelligent monitoring within digital manufacturing workflows. Full article

The high installation and operational costs of reference-grade air quality monitoring systems have accelerated the widespread adoption of low-cost sensors (LCS). However, their susceptibility to environmental influences, temporal drift, and measurement uncertainty necessitates robust calibration approaches to ensure reliable measurements. Although machine learning (ML)-based calibration methods have been widely investigated, most existing implementations rely on static analytical workflows and require programming expertise, which limits their accessibility for many domain specialists. To simplify and standardize the calibration process for low-cost air quality sensors, this study presents Air Quality Multi-Model Calibration (AQ-MultiCal), an interactive, no-code platform. The platform provides a unified environment for evaluating 14 regression models, performing automated hyperparameter optimization, and conducting comparative performance analysis through an intuitive graphical interface supported by interactive visualization tools. The platform is validated using CO₂ measurements collected from January and February 2025. Experimental results indicate that the optimized k-nearest neighbors (kNN) model achieved the best performance, with a coefficient of determination of R² = 0.990 with low prediction error. These results demonstrate that AQ-MultiCal enables accurate sensor calibration and systematic comparison of ML models while improving the accessibility of ML-based calibration through an open-source platform designed for domain experts without programming expertise. Full article

The objective of this review is to deepen the understanding and mastery of non-mass breast pathologies, enabling ultrasonographers to enhance diagnostic accuracy and improve their capabilities in image analysis and clinical interpretation. Narrative means have been used to synthesize evidence in this review. Currently, “non-mass breast lesions” are not included in ultrasound terminology of the 5th Edition Breast Imaging Reporting and Data System (BI-RADS). Although multiple classification systems have been proposed in the literature, there remains no standardized ultrasound definition or malignant risk grading for non-mass lesions. The ultrasound features of benign and malignant non-mass breast lesions are often subtle and partially overlapping, complicating differential diagnosis and impacting clinical evaluation and management. This paper reviews the ultrasound definitions and classifications of non-mass breast lesions, exploring the correlation between their ultrasound features and pathological histology as well as malignant risk. It also discusses the diagnostic values of conventional ultrasound, automated breast ultrasound, ultrasound elastography, and contrast-enhanced ultrasound for non-mass breast lesions. Finally, it compares the diagnostic accuracy of various ultrasound-guided needle biopsy techniques for non-mass lesions. Through the synthesis and summarization of the relevant literature, this paper aims to enhance the diagnostic proficiency of sonographers in evaluating non-mass breast lesions. Full article

With the growing adoption of data-driven workflows and the need to compare numerous interior design alternatives in housing renewal, scalable and consistent assessment of interior space quality is increasingly important; however, current practice still depends on manual scoring and expert judgment. To address this gap, we propose an automation-ready framework that evaluates interior space quality from visual data. We construct the Functionality–Healthiness–Aesthetics Spatial Interior Dataset-10K (FHASID-10K) with 13,962 images for systematic validation. Three sub-models quantify functionality via space utilization and circulation smoothness, healthiness via detection of health-related visual elements, and aesthetics via semantic visual representations with regression-based prediction. Dimension scores are standardized and fused using the analytic hierarchy process (AHP) and the technique for order preference by similarity to ideal solution (TOPSIS) to produce a comprehensive score for ranking and grading. Experiments show stable score distributions and clear differentiation across space categories and style–space combinations. A gradient-boosted decision tree (GBDT) surrogate reconstructs the fused score with high accuracy (test R² = 0.9992; MSE = 1.1 × 10⁻⁵), and human-subject evaluation shows strong agreement with overall-quality ratings (r = 0.760, p < 0.001). Overall, the framework enables scalable benchmarking, scheme comparison, and decision support. Full article

The aim of this study was to design and validate an automated 5 L prototype Stirred-Tank Photobioreactor (ST-PBR) dedicated to the two-stage cultivation of the microalga Haematococcus pluvialis. The classic limitations of stirred-tank reactors (such as high shear stress and suboptimal light penetration) were overcome through precise phase-controlled illumination (60 and 300 μmol m⁻² s⁻¹) and the implementation of an advanced embedded control system integrated with Keysight VEE Pro 9.33 software. The design features an innovative mixing system utilizing a dual marine impeller driven by a brushless motor—operating at a mathematically defined tip speed of 0.48 m/s to preserve cellular integrity—alongside a precise gas dosing strategy (pH-stat) employing medical-grade components. Process verification demonstrated highly stable operation, maintaining a dry biomass concentration of 1.315 g/L with no recorded sedimentation, while achieving a highly competitive astaxanthin biosynthesis yield of 4.12% dry weight (DW). Furthermore, enzymatic extraction facilitated the recovery of a product with high biological activity, as confirmed by an increase in equine adipocyte viability up to 128.1 ± 3.1% in in vitro MTS assays, highlighting its potential for veterinary nutraceutical applications. The developed solution represents a scalable, cost-effective, and viable alternative to advanced tubular photobioreactors. Full article

Deep learning is increasingly integrated into oral rehabilitation workflows, particularly in implant planning, prosthodontic design automation, and peri-implant diagnosis. However, reported performance is heterogeneous and difficult to compare across tasks, modalities, and validation designs. The goal of this study was to critically analyze deep learning architecture families applied to oral rehabilitation and to provide task-driven selection guidance supported by an evidence table reporting dataset characteristics, validation strategy, and performance metrics. A focused narrative review was conducted using transparent, database-specific search criteria (final n = 10 included studies), emphasizing implant planning (cone–beam computed tomography [CBCT]-based segmentation), prosthodontic design (intraoral scan [IOS]/mesh inputs), and peri-implant diagnosis (periapical/panoramic radiographs). Evidence certainty for each clinical task was assessed using GRADE-informed ratings (High/Moderate/Low/Very Low). Extracted variables included clinical task, imaging modality, dataset size, architecture, validation strategy (internal vs. internal + external), split level, ground truth protocol, and performance metrics. A structured computational and hardware feasibility analysis was conducted for each architecture family to support real-world deployment planning. Encoder–decoder networks (U-Net/nnU-Net) dominate CBCT segmentation for implant planning, while detection architectures (Faster R-CNN, YOLO) support implant localization and peri-implant assessment on radiographs. Generative models (3D GANs, transformer-based point-to-mesh networks) enable crown design from three-dimensional scans. Hybrid CNN–Transformer architectures show promise for multimodal CBCT–IOS fusion, though direct evidence from the included studies remains limited to a single study. External validation remains uncommon yet essential given the risk of domain shift. In conclusion, architecture selection should be anchored to task geometry (2D vs. 3D), artifact burden, and required clinical output type. Reporting standards should prioritize dataset transparency, validation rigor, multi-center external testing, and uncertainty-aware outputs. Full article

Objective: To develop and validate an artificial intelligence (AI) system for automated lens opacities classification system III (LOCS III)-based grading of all three major cataract subtypes using anterior segment optical coherence tomography (AS-OCT). Methods: This is a single-center cross-sectional study. AS-OCT images were collected and manually graded by ophthalmologists according to LOCS III. The dataset was randomly split into training, validation, and test sets. We propose a novel multi-granularity mask-guided network (MMNet) that jointly performs lens substructure segmentation and severity grading. The model’s performance was assessed on an independent test set for automatic grading of cortical cataract (CC), nuclear cataract (NC), and posterior subcapsular cataract (PSC) and the grading performance of the proposed method against ophthalmologists was also evaluated. The model’s interpretability was assessed via attention heatmaps and feature visualization. Results: The proposed MMNet exhibited high agreement with ground truth conducted through gold standard. The proportions of predictions with an absolute error < 1.0 for three subtypes range from 83.02% to 89.94%. The model’s grading accuracy for cataract subtypes was between 82.20 ± 1.41% and 89.76 ± 1.31% among the three subtypes, the Area Under the Curve (AUC) was between 0.954 (95% CI, 0.952–0.969; p < 0.001) and 0.973 (95% CI, 0.964–0.985; p < 0.001). The MMNet shows a satisfactory mean absolute error (MAE) of 0.14 ± 0.35 in CC, 0.10 ± 0.30 in NC, and 0.17 ± 0.38 in PSC grading. It also achieved a fast grading speed of 0.0178 s/image against manual grading. Conclusions: The proposed AI model presented advanced performance on AS-OCT images in automated LOCS III-based cataract grading for CC and NC, and also showed feasibility in PSC assessment. Full article

Steel slags are major by-products of steelmaking, and their variable composition complicates recycling and valorization strategies. This study investigates four representative slag samples obtained from different production pathways at an industrial steel plant in Uzbekistan, using a combined multi-scale characterization approach. Bulk elemental composition was determined using X-ray fluorescence (XRF), while microstructural and phase-level analysis was carried out using scanning electron microscopy with energy-dispersive spectroscopy (SEM–EDS), including both point analysis and automated phase mapping. The XRF results revealed two distinct compositional groups, with one slag dominated by Mn–Si–O chemistry and three slags characterized by high Ca content. SEM–EDS phase mapping further resolved these differences at the microscale, identifying manganese silicate and oxide phases in the Mn-rich slag, Ca–F–O dominant phases in two slags associated with fluorite flux addition, and a more heterogeneous Ca-based system with localized enrichments of Mn, Zn, and Cu in the fourth sample. The combined results demonstrate that slag composition strongly reflects steel grade and fluxing practice. The integration of XRF and SEM–EDS provides a robust framework for linking bulk chemistry with phase distribution, improving slag classification and supporting informed decisions for reuse and environmental management. Full article

This study proposes a new deep learning-based approach for detecting pitting corrosion on stainless-steel sheet pile surfaces in drainage channels. Conventional ultrasonic thickness measurement methods cannot detect microscopic pitting corrosion that occurs before measurable thickness reduction. The research develops an automated detection system using visible images captured with smartphone cameras and U-net semantic segmentation. Two stainless steel grades (SUS410 and SUS430) were exposed for 5 years to a brackish water environment and analyzed. The deep learning approach achieved F1-scores of 0.831 (SUS410) and 0.808 (SUS430), outperforming binary thresholding methods (F1-scores: 0.407 and 0.329, respectively). Data augmentation improved performance by 1–3 percentage points. The method enabled non-destructive, quantitative assessment of early-stage corrosion using readily available equipment, providing a practical tool for infrastructure maintenance and long-term durability evaluation. Full article

Background/Objectives: Perirenal fat (PRF) constitutes a critical yet understudied component of the tumor microenvironment in clear cell renal cell carcinoma (ccRCC). While radiomics enables non-invasive tissue characterization, whether PRF-derived features can simultaneously predict both TNM stage and histological grade, and whether optimal peritumoral distances differ between these distinct biological targets, remains unexplored in the literature. Methods: This multi-cohort retrospective study included 474 histopathologically confirmed ccRCC patients from three independent datasets (2007–2023). Automated nnU-Net segmentation delineated tumors and kidneys. Concentric PRF regions were systematically generated at 1–10 mm radial distances, yielding 18 distinct regions of interest. From each ROI, 1409 radiomic features were extracted using PyRadiomics. Sequential feature selection employed correlation filtering, SHAP-guided elimination, and LASSO regularization. Multiple machine learning classifiers underwent hyperparameter optimization with rigorous cross-cohort validation. Results: Systematic ROI screening revealed target-specific optimal distances: 4 mm PRF for TNM staging versus 10 mm PRF for histological grading. For staging, the integrated model (tumor + PRF radiomics + clinical variables) achieved AUC 0.829 (95% CI 0.781–0.877), sensitivity 80.2%, and specificity 67.8%. For grading, the combined model achieved AUC 0.780 (95% CI 0.598–0.962), sensitivity 79.7%, and specificity 63.3%, significantly outperforming all single-compartment models (DeLong p < 0.001). Conclusions: This study establishes that PRF radiomics enables accurate simultaneous non-invasive prediction of both TNM stage and histological grade in ccRCC. The novel discovery that optimal peritumoral distances differ substantially by prediction target (4 mm versus 10 mm) suggests distinct biological underpinnings for stage- and grade-related microenvironmental alterations, with important methodological implications for radiomic model development in oncology. Full article

Automated scoring of open-ended questions is an important research direction in educational technology and artificial intelligence, as manual grading is time-consuming and often subject to inter-rater variation. This paper proposes an AI-based framework for automated scoring that combines large language models (LLMs), Retrieval-Augmented Generation (RAG), analytical rubrics, and structured machine-readable output within a Moodle-supported e-learning environment. The framework is designed to support context-grounded and criterion-based evaluation by combining the student response, retrieved instructional context, and rubric-defined scoring criteria within a controlled assessment workflow. The proposed approach aims to improve the consistency, traceability, and practical applicability of automated scoring for open-ended responses. To examine its performance, an experimental study was conducted in a real university setting involving a five-task open-ended examination. AI-generated scores were compared with independent human scores using agreement, reliability, correlation, and error metrics. The results indicate a strong level of agreement between automated and expert scoring within the tested setting, together with relatively low average deviation. These findings suggest that the proposed framework has practical potential for supporting automated assessment in digital learning environments, while also highlighting the importance of careful interpretation within the scope of the experimental design. Full article

Accurate classification of fruit maturity is essential for automated grading and robotic manipulation in modern greenhouse cultivation. Most existing methods rely on crop-specific models, severely restricting their scalability in multi-crop scenarios. To overcome this limitation, this study presents SCEA-YOLO, a unified and efficient instance segmentation framework built on YOLOv11s-seg, for simultaneous maturity classification of tomatoes and sweet peppers. To boost feature discrimination, reduce computational redundancy, and alleviate class imbalance, SCEA-YOLO integrates spatial-channel reconstruction convolution and an efficient multi-scale attention mechanism, while replacing the original detection head with the proposed EA-Head. The model is evaluated on a hybrid dataset captured under diverse greenhouse conditions, including varying illumination, fruit occlusion, and overlapping canopies. Its robustness to different viewing angles and camera distances is further validated via deployment on an automated grading robot. Compared with the baseline, SCEA-YOLO enhances classification precision and mAP_50–95 by 5.3% and 2.3% for tomatoes, and 1.2% and 1.4% for sweet peppers, respectively. With only 33.2 GFLOPs, the model satisfies real-time inference demands. Benefiting from its lightweight structure and real-time performance, SCEA-YOLO can be readily deployed on embedded systems and robotic platforms. It offers a practical, unified, and scalable solution for intelligent fruit maturity evaluation in multi-crop greenhouse production. Full article

To address the low accuracy of traditional freshness detection/grading and poor adaptability to different shell colors in the duck egg industry, this study developed a non-destructive detection model and an integrated device for duck egg freshness based on machine vision combined with eggshell optical property analysis. A four-sided yolk transmission imaging system was designed, and accurate yolk region segmentation was achieved via grayscale conversion, a weighted improved Otsu algorithm for whole-egg segmentation, histogram equalization enhancement, and K-means clustering in the LAB color space. A relational model between the average four-angle yolk projected area ratio and Haugh Units (HU) freshness grades was constructed, with grading thresholds determined by constrained optimization combined with the Youden index to balance food safety and grading accuracy. Experimental results showed the model achieved an overall freshness grade discrimination accuracy of 91.3%, with a sensitivity of 97.1% and specificity of 98.9% for inedible Grade B (HU < 60) duck eggs and below. An automated testing device was further developed, adopting a roller-rotating motor collaborative mechanism for automatic flipping and imaging, and equipped with a 10 W/5500 K LED cool white light source to solve the problem of poor adaptability to different shell colors. The device achieved an overall discrimination accuracy of 88.5% with a detection time of ≤5 s per egg, and its host computer can real-time output the yolk area ratio, predicted HU value, and freshness level. This study provides a high-precision and low-cost technical solution for the refined grading of the poultry egg industry. Full article

In the fish grading process, traditional mechanical sorting devices tend to cause fish stacking, collisions, and increased stress responses, seriously affecting fish health and commercial value. This paper designs a power-free fish pre-sorting device based on a spiral chute structure, achieving automatic and gentle separation and output driven by the fish’s own weight and water flow; it constructs a multi-stage dynamic model of fish in the spiral chute to analyze the forces and motion patterns; and it introduces an innovative DEM-SPH coupled numerical simulation technology to accurately simulate the complex interactions between fish and water, thereby revealing the self-sorting mechanism of fish inside the device. By setting different conditions such as fish length and water layer thickness, the sorting effect and stability of the device are systematically verified. The results show that this spiral power-free sorting device can effectively achieve automatic spacing separation of fish, reducing collisions and stress responses; fish of 130 mm length have better sorting stability under a water layer thickness of 3–5 cm, and the minimum initial release spacing for effective operation of the device is determined to be 0.11 m. Full article

Computed tomography (CT) enables non-destructive insight into internal log structure, yet fully automated interpretation of CT images remains limited by inconsistent annotations, boundary ambiguity, and insufficient spatial context in 2D slice-based analysis. These challenges restrict the industrial deployment of deep learning for wood quality assessment. This study applies artificial intelligence (AI) and deep learning to the automated analysis of computed tomography (CT) scans of wood logs for detecting internal qualitative features and segmenting bark. Using convolutional neural networks (CNNs), trained models accurately distinguish healthy and damaged regions and segment bark, including discontinuous parts. We introduce a novel pseudo-spatial representation by merging consecutive slices into red–green–blue (RGB) format, which improves prediction accuracy and model robustness across logs. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) highlights regions contributing most to defect detection, particularly knots. Comprehensive evaluation using Sørensen–Dice similarity coefficients and confusion matrices confirms the effectiveness of the proposed approach under industrial conditions. These findings demonstrate that AI-driven CT image analysis can address key limitations of current log-grading workflows and enable more reliable, objective, and scalable quality assessment for timber-dependent economies. Full article