Search Results (2,985)

Background: Preterm birth remains a major cause of perinatal morbidity and long-term developmental complications. Existing prediction methods often lack individualized assessment and have limited capability to integrate multi-source maternal–fetal information. This study aims to develop a personalized preterm birth risk prediction model and to construct a visual, interactive digital twin platform that enhances clinical communication and supports early risk identification. Methods: A total of 1157 structured clinical records collected from 2020 to 2024 were preprocessed through automated feature typing, missing-value handling, and normalization. Two complementary machine-learning models—FT-Transformer and Light Gradient Boosting Machine (LightGBM)—were trained and calibrated to produce probabilities. Their outputs were fused using a Stacking Logistic Regression framework to improve prediction stability and calibration. A 3D visualization module was developed using 3ds Max, PyQt6, and PyVista to generate personalized uterine–fetal models based on fetal position, placental location, and Biparietal Diameter (BPD), enabling synchronized display of prediction results. Results: The fused model achieved an AUC of 0.820, PR-AUC of 0.405, a Brier score of 0.040, and an expected calibration error (ECE) of 3.39 × 10⁻³, demonstrating superior discrimination and probability reliability compared with single models. The interactive platform supports real-time data input, risk prediction, and adaptive 3D rendering, providing clear and intuitive visual feedback for clinical interpretation. Conclusions: The integration of machine learning fusion and digital twin visualization enables individualized assessment of preterm birth risk. The system improves model accuracy, enhances interpretability, and offers a practical tool for clinical follow-up, risk counseling, and maternal health education. Full article

Background/Objectives: Neuromuscular fatigue (NMF) can impair manual dexterity and strength in healthcare professionals. Due to their high physical and cognitive workloads, physiotherapists (PTs) are particularly susceptible to NMF. This study investigated whether NMF, expressed as changes in manual dexterity and grip strength, occurs over a workday and across a workweek in PTs, and explored its relationship with stress and sleep quality. Methods: A total of 43 full-time PTs (25 female, mean age 37.72 ± 11.94 years) were recruited. Manual dexterity was assessed using the Functional Dexterity Test (FDT), while maximal grip strength (MGS) was measured by a hand dynamometer. Reliability was evaluated on a subgroup using Intraclass Correlation Coefficients (ICC_3,1) and Standard Error of Measurement (SEM). Evaluations were conducted at the beginning and at the end of the work shift, on Monday and Friday. Subjective fatigue, perceived stress, and sleep quality were also recorded. Results: The FDT showed excellent intra-rater reliability (ICC > 0.93; SEM < 0.94 s). FDT performance was significantly slower on Friday evening compared to all other time points (p < 0.01), exceeding the minimal detectable change thresholds. No significant changes were observed in MGS across the week. Perceived stress was strongly correlated with fatigue levels on Monday (ρ = 0.731) and Friday (ρ = 0.612) evenings. Sleep quality and professional experience did not correlate with performance changes. Conclusions: PTs experience a significant decline in manual dexterity by the end of the workweek, suggesting an accumulation of NMF. While MGS remains stable, fine motor control is more sensitive to fatigue. Psychosocial stress appears to be a major driver of perceived fatigue in this population. Full article

Non-line-of-sight (NLOS) propagation remains a major obstacle to high-accuracy ultra-wideband (UWB) indoor positioning. To address this issue, this study investigates solutions from two complementary perspectives: NLOS identification and error mitigation. First, an NLOS signal classification model is proposed based on multidimensional statistics of the channel impulse response (CIR). The model incorporates an attention mechanism and an improved snake optimization (ISO) algorithm, achieving significantly enhanced classification accuracy and robustness. For error mitigation, a UKF–BiLSTM dual-directional mutual calibration framework is proposed to dynamically compensate for NLOS errors. The framework embeds the constant turn rate and velocity (CTRV) motion model within an unscented Kalman filter (UKF) to enhance trajectory modeling. It establishes a bidirectional correction loop with a bidirectional long short-term memory (BiLSTM) network. Through the synergy of physical constraints and data-driven learning, the framework adaptively suppresses NLOS errors. Experimental results show that the proposed framework achieves state-of-the-art–comparable performance with improved model efficiency in complex indoor UWB positioning scenarios. Full article

Background/Objectives: Medication-related safety incidents rank among the most prevalent patient safety concerns globally. In addition to healthcare professionals, patients also play a vital role in ensuring safe medication practices. To effectively engage them, it is essential to gain a deeper understanding of their knowledge and perspectives. Methods: We conducted a netnography-based mixed-method content analysis study within the Hungarian online environment to identify key patient concerns. A total of 5174 relevant comments and discussions were analyzed (from 14 August 2020 to 14 August 2023), utilizing a medication safety framework based on Glies et al. The analysis was confined to publicly accessible online content related to oral medications and did not include demographic information about commenters. Results: The framework was applicable, though its representation was uneven. Patients predominantly focused on issues related to Access to services and Communication. Online discussions were primarily dominated by patients, with contributions from relatives and healthcare professionals being comparatively limited. The majority of concerns pertained to prescription medications, particularly in the fields of gynecology, internal medicine, and gastroenterology. ATC codes G and A were most frequently referenced, corresponding to the healthcare domains discussed. Conclusions: Initiatives aimed at enhancing medication safety should prioritize improving access and communication. Patients must be empowered as active agents in safety efforts; they can aid in preventing errors, reporting incidents, and offering feedback. Their engagement supports organizational learning and promotes safer healthcare delivery. Full article

Reliable observation of water resources is a major challenge for sustainable development, particularly in the river-centric deltaic countries like Bangladesh, where the data is generally scarce. Leveraging operational satellites, this study presents a real-time capable water level (WL), discharge (Q), and floodplain monitoring framework implemented for the Brahmaputra River in Bangladesh. The multi-satellite approach presented here combined satellite altimetry, synthetic aperture radar (SAR), and optical imagery. A set of WL time series is obtained first from Jason-2/3 and Sentinel-3 altimetry, while a combination of Sentinel-1 SAR and Sentinel-2 optical images is used to extract the floodplain extent. Seasonal Rating Curve (RC) models are then developed to estimate Q from the river WL (altimetry) and width (imagery). The altimetry WL measurement is further complemented by the width-based Q utilizing an inverse RC. Furthermore, the water level is combined with a floodplain map to extract floodplain topography and its evolution. The proposed framework provides consistent and reliable observations in the Brahmaputra River, with a bias, root mean-squared errors (RMSEs), and correlation coefficient of 0.03 m, 0.68 m, and 0.96 for WL, and −168.22 m³/s, 4161.46 m³/s, and 0.97 for Q, respectively, relative to a mean discharge of approximately 30,000 m³/s. The locations of high erosion–accretion across the river reach are also well-captured in the evolving floodplain maps. By integrating multiple satellite altimetry missions with SAR and optical imagery, the multi-satellite approach reduces the effective monitoring interval for both water level and discharge from approximately 10 days (single-mission altimetry) to about 4 days, enabling improved capture of extreme events such as floods. As the operational satellites used in this study are expected to provide long-term observations, the proposed framework supports sustainable monitoring of floodplain dynamics in Bangladesh and other similar data-poor environments, towards informed water management under ongoing climatic and anthropogenic changes. Full article

Knee disorders are a major indication for musculoskeletal imaging, yet MRI reliability remains constrained by signal nonuniformity, motion artefacts, protocol variability, and reader-dependent effects. This study presents an integrated two-vector framework that couples (i) a fuzzy diagnostic control-risk model with (ii) a quantitative digital-maturity assessment to strengthen MRI-based diagnosis of knee pathology. The vertical vector characterizes organizational readiness through a weighted fuzzy aggregation of six capability agents (technical, information and analytical, mathematical/model, metrological, human resources, and software support). The horizontal vector estimates producer’s and consumer’s risks as misclassification probabilities relative to an acceptance boundary, driven by measurement/interpretation uncertainty, variability of the decision threshold, and the ratio of instrumental to physiological dispersion. Simulation results indicate that error probabilities increase sharply when threshold uncertainty exceeds 20–25% and rise by approximately 15–20% as the standard-deviation ratio approaches unity. To connect diagnostic reliability with downstream mechanics, a FE analysis of the tibial insert in TKA under F = 1150 N at 0° flexion predicts a peak contact pressure of 85.449 MPa and a maximum UHMWPE von Mises stress of 43.686 MPa, identifying wear-critical contact zones. Overall, the proposed framework provides interpretable quantitative targets for QA, protocol refinement, and resource allocation in radiology services undergoing digital transformation, and offers a reproducible pathway for linking imaging reliability to biomechanical risk. Full article

Accurate and timely crop yield estimation remains a major challenge in agriculture due to the limitations of traditional field-based methods, which are labor-intensive, destructive, and unsuitable for large-scale applications. While recent advances in Unmanned Aerial Vehicles (UAVs) and Deep Learning (DL) have enabled non-destructive and scalable alternatives, melons (Cucumis melo L.) remain relatively understudied, and datasets for yield estimation are scarce. This study presents a computer vision pipeline for UAV-based fruit detection and yield estimation in melon crops. High-resolution UAV RGB imagery was processed using YOLOv12 (You Only Look Once, version 12) for fruit detection, followed by a volume-based regression model for weight estimation. The experiment was conducted during the May–August 2025 growing season in Apulia, southern Italy. The detection model achieved high accuracy, with strong agreement between estimated and actual fruit counts (R² = 0.99, MAPE = 5%). The regression model achieved an R² of 0.79 for individual weight estimation and a total yield error of 2.9%. By addressing the scarcity of melon-specific data, this work demonstrates that integrating UAV imagery with deep learning provides an effective and scalable approach for accurate yield estimation in melons. Full article

The detection of defects in Printed Circuit Boards (PCBs) is a critical yet challenging task in industrial quality control, characterized by the prevalence of small targets and complex backgrounds. While deep learning models like YOLOv5 have shown promise, they often lack the ability to quantify predictive uncertainty, leading to overconfident errors in challenging scenarios—a major source of false alarms and reduced reliability in automated manufacturing inspection lines. From a Bayesian perspective, this overconfidence signifies a failure in probabilistic calibration, which is crucial for trustworthy automated inspection. To address this, we propose MFE-YOLO, a Bayesian-enhanced detection framework built upon YOLOv5 that systematically integrates uncertainty-aware mechanisms to improve both accuracy and operational reliability in real-world settings. First, we construct a multi-background PCB defect dataset with diverse substrate colors and shapes, enhancing the model’s ability to generalize beyond the single-background bias of existing data. Second, we integrate the Convolutional Block Attention Module (CBAM), reinterpreted through a Bayesian lens as a feature-wise uncertainty weighting mechanism, to suppress background interference and amplify salient defect features. Third, we propose a novel FIoU loss function, redesigned within a probabilistic framework to improve bounding box regression accuracy and implicitly capture localization uncertainty, particularly for small defects. Extensive experiments demonstrate that MFE-YOLO achieves state-of-the-art performance, with mAP@0.5 and mAP@0.5:0.95 values of 93.9% and 59.6%, respectively, outperforming existing detectors, including YOLOv8 and EfficientDet. More importantly, the proposed framework yields better-calibrated confidence scores, significantly reducing false alarms and enabling more reliable human-in-the-loop verification. This work provides a deployable, uncertainty-aware solution for high-throughput PCB inspection, advancing toward trustworthy and efficient quality control in modern manufacturing environments. Full article

Lanthanide-based single-molecule magnets are promising candidates for potential applications. Their magnetism is governed by ligand-field splittings, which may require up to 27 ligand-field parameters for accurate modeling. Determining these parameters reliably from measured data is a major challenge, for which machine learning approaches offer promising solutions. We provide an overview of these approaches and present our perspective on addressing the inverse problem relating experimental data to ligand-field parameters. Previously, a machine learning architecture combining a variational autoencoder (VAE) and an invertible neural network (INN) showed promise for analyzing temperature-dependent magnetic susceptibility data. In this work, the VAE-INN model is extended through data augmentation to enhance its tolerance to common experimental inaccuracies. Focusing on second-order ligand-field parameters, diamagnetic and molar-mass errors are incorporated by augmenting the training dataset with experimentally motivated error distributions. Tests on simulated experimental susceptibility curves demonstrate substantially improved prediction accuracy and robustness when the distributions correspond to realistic error ranges. When applied to the experimental susceptibility curve of the complex ${\mathrm{Al}}_2^{\mathrm{III}}$${\mathrm{Er}}_2^{\mathrm{III}}$, the augmented VAE–INN recovers ligand-field solutions consistent with least-squares benchmarks. The proposed data augmentation thus overcomes a key limitation, bringing the ML approach closer to practical use for higher-order ligand-field parameters. Full article

Due to the significant potential of crowd flow prediction in the domains of commercial activities and public management, numerous researchers have commenced investing in pertinent investigations. The majority of existing studies employ recurrent neural networks, long short-term memory, and similar models to achieve their objectives. Despite the advancements in predictive modeling, the objective of many existing studies remains in the minimization of distance errors. This focus, however, introduces three notable limitations in prediction outcomes: (1) the predicted location may represent an average of multiple points rather than a distinct target, (2) the results may fail to reflect actual user behavior patterns, and (3) the predictions may lack geographic plausibility. To address these challenges, we developed a Transformer-based model integrated with adversarial network architecture. The Transformer component has shown considerable effectiveness in forecasting individual movement trajectories, while the discriminator within the adversarial framework guides the generator in refining outputs to better reflect user habits and spatial rationality. Full article

Effective and sustainable livestock management within Mediterranean ecosystems depends heavily on accurate and timely monitoring of sward composition. Traditionally, this task has relied on human observers who must traverse large and often rugged areas to identify the distribution of grasses, legumes, shrubs, and other plant groups. However, this approach is not only labor-intensive and slow but also susceptible to substantial human error, especially when observations must be repeated frequently or carried out under difficult field conditions. In the present study, an alternative method that integrates wearable cameras with modern computer-vision techniques to automatically recognize pasture plant species through an edge device present in farm premises was investigated. Additionally, the feasibility of achieving reliable classification performance on resource-constrained edge devices was evaluated. To this end, five widely used pre-trained convolutional neural networks were compared against a lightweight custom model developed entirely from scratch. The results demonstrated that ResNet50 delivered the strongest classification accuracy, achieving a Matthews Correlation Coefficient (MCC) of 0.992. Nonetheless, the custom lightweight model proved to be a practical compromise for real-world field use, reaching an MCC of 0.893 while requiring only 6.24 MB of storage. The inference performance on Raspberry Pi 4, Raspberry Pi 5, and Jetson Orin Nano platforms was also evaluated, revealing that the Selective Search stage remains a major computational limitation for achieving real-time operation. The results obtained confirm the possibility of implementing a plant identification system in agricultural facilities without the need to transfer images to a cloud-based application. Full article

The problem of the post-harvest loss of perishable products has been a loss facing food security, especially in areas that lack adequate cold chain facilities. This issue is directly connected with sustainability objectives because post-harvest losses are the major source of food wastage, unneeded energy use, and related greenhouse gas emissions. Cold storage with phase-change material (PCM) is a promising alternative, as it aims at stabilizing temperatures and enhancing energy consumption, but current analyses of performance have been conducted through experimental testing and computational fluid dynamic (CFD) simulations, which are precise but computationally expensive. To handle this drawback, the current work constructs a machine learning predictive model to predict the dynamics of charging and discharging temperature of PCM cold storage systems. Four regression models, namely Random Forest, Extreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), and K-Nearest Neighbors (KNNs), were trained and tested on experimental datasets that were obtained for varying storage layouts. The various error and accuracy measures used to determine model performance comprised MSE, MAE, R², MAPE, and percentage accuracy. The findings suggest that Random Forest provides the best accuracy during both the charging and the discharging process, with the highest R² values of over 0.98 and with minimal mean absolute errors. The KNN model was competitive in the discharge process, especially in cases of consistent thermal recovery patterns, and XGBoost was consistent in layout accuracy. However, SVR had relatively lower robustness, particularly when using nonlinear charged dynamics. Among the evaluated models, the Random Forest algorithm demonstrated the highest predictive accuracy, achieving coefficients of determination (R²) exceeding 0.98 for both charging and discharging processes, with mean absolute errors below 0.6 °C during charging and 0.3 °C during discharging. This paper has proven that machine learning is an efficient surrogate to CFD and experimental-only methods and can be used to predict the thermal behavior of PCM quickly and precisely. The proposed framework will allow for developing cold storage systems based on energy efficiency, low costs, and sustainability, especially in the context of decentralized and resource-limited agricultural supply chains, with the help of quick and data-focused forecasting of PCM thermal behavior. Full article

CO₂ injection success hinges on the injectivity index, a major determinant of storage feasibility. This study develops a machine learning (ML)-driven framework optimized for CO₂ injectivity prediction, benchmarking its robustness and real-world applicability against an empirical correlation developed in the literature. The framework is applied to the Entrada Formation in the San Juan Basin, a laterally extensive sandstone unit with limited structural complexity across most of the basin, except for localized uplift in the Hogback region. A numerical model was calibrated to perform sensitivity analysis to identify the dominant parameters influencing injectivity. A dataset of these parameters generated through experimental design informs the development of several ML-based proxies and the best model is selected based on error metrics. These metrics include coefficient of determination (R²), mean absolute error (MAE), and mean squared error (MSE). The effective permeability-thickness product was obtained by the Peaceman’s well model, fractional flow slope, and Dykstra–Parsons coefficient were identified as the most influential parameters impacting the objective function. Train–test and blind test validation identified the Ridge model as the best, achieving an R² ≈ 0.994. The Ridge model which was used to map the Entrada Formation closely matches field-based correlations in the literature, confirming both its physical validity and the Entrada Formation’s strong injectivity potential, with slight deviations explained by the inclusion of additional parameters. This study reduces dependence on computationally intensive simulations while improving prediction accuracy. By benchmarking against established correlations, it enhances model reliability across diverse reservoir conditions. The proposed framework enables rapid, data-driven well placement and feasibility evaluations, streamlining decision-making for CO₂ storage projects. Full article

An extraordinary episode is a torrential rainfall event that produces significant societal impacts, which poses a major natural hazard in the western Mediterranean, particularly along the Valencia coast. This study evaluates the feasibility and added value of an explicitly spatial approach for estimating return periods of extraordinary precipitation in the Júcar and Turia basins, moving beyond traditional point-based or micro-catchment analyses. Our methodology consists of progressive spatial aggregation of time series within a basin to better estimate return periods of exceeding specific catastrophic rainfall thresholds. This technique allows us to compare 10 min rainfall data of a reference station (e.g., Turís, València, 29 October 2024 catastrophe) with long-term annual maxima from 98 stations. Temporal structure is characterized using the fractal–intermittency n-index, while tail behavior is modeled using several extreme-value distributions (Gumbel, GEV, Weibull, Gamma, and Pareto) and guided by empirical errors. Results show that $n\approx 0.3$–0.4 is consistent for extreme rainfall, while return periods systematically decrease as stations are added, stabilizing with about 15–20 stations, once the relevant spatial heterogeneity is sampled. Specifically, the probability of exceeding extraordinary thresholds is between 3 and 10 times higher for the areal than the point approach, so recurrence of a catastrophe would be once a few decades rather than centuries. Overall, the results demonstrate that spatially integrated return-period estimation is operational, physically consistent, and better suited for basin-scale risk assessment than purely point-based approaches, providing a relevant baseline for interpreting recent catastrophic events in the context of ongoing climatic warming in the Mediterranean region. Full article

The production and assembly of large engineering structures, many requiring tight tolerances, demand accurate long-distance measurements. This poses a major challenge for metrologists across industries such as energy, aviation, automotive, and machinery. Contact measurements provide high accuracy but are slow, as tactile probes must be moved over large distances. Optical methods are much faster, yet their effective range is usually limited to a few meters, and they generally offer lower accuracy. Measurements of large-scale components are further complicated by varying environmental conditions (e.g., temperature gradients) and the accumulation of different error sources, making high-accuracy measurements difficult to achieve. These challenges motivated the authors to develop hybrid measurement systems (HMS) and methods for improving their accuracy. This paper describes the steps taken to build an HMS combining a large-volume, high-accuracy coordinate measuring machine with a structured-light scanner. It also presents a dedicated method for determining measurement uncertainty in HMS, based on a multiple-measurement strategy. A series of tests were performed on material standards with various shapes, dimensions, and geometric features, using both contact and optical systems. The measurement uncertainties were then evaluated using the developed method. Finally, the method was validated through tests conducted on a selected large-scale engineering object. Full article