Search Results (2,181)

The accurate and non-invasive measurement of moisture content in wood is essential for the preservation of historical and artistic artifacts. This study presents the calibration of a planar Microwave Planar Capacitive Coupled Ring Resonator (MPCCRR) designed to indirectly and non-destructively assess the water content in wood samples. The method relies on analyzing shifts in the resonant frequencies and variations in the transmission parameter |S21| resulting from changes in the material’s dielectric permittivity. After preliminary characterization via parametric simulations (εr = 1–10) and validation with low-permittivity reference materials, the sensor was tested on three wood species (poplar, fir, beech), including measurements at two sensor positions and with different grain orientations. The results demonstrate a monotonic, repeatable response to increasing moisture content with frequency shifts up to ≈220 MHz and normalized sensitivities ranging from 3 to 9 MHz/% water content, depending on species and measurement position. Position 2 showed the greatest sensitivity due to stronger field–sample interaction, while Position 1 provided a quasi-isotropic response with excellent repeatability. Linear regression analyses revealed good correlations between the frequency shifts and the gravimetric water content (R² ≥ 0.85). The MPCCRR sensor therefore proves to be a promising tool for the non-invasive monitoring of wood moisture, which is particularly suitable for the low-moisture range encountered in cultural heritage conservation, with an estimated moisture uncertainty of 0.12–0.35% under controlled laboratory conditions. Full article

Industrial visual anomaly detection remains challenging because practical inspection systems must achieve high detection accuracy while operating under highly imbalanced data, diverse defect patterns, limited computational resources, and increasing demands for interpretability. This work aims to develop a lightweight yet effective and explainable anomaly detection framework for industrial images in settings where a limited number of labeled anomalous samples are available. We propose a dual-branch feature-based supervised ensemble method that integrates complementary representations: a PCA branch to capture linear global structure and a scattering branch to model multi-scale textures. A heterogeneous pool of classical learners (SVM, RF, ET, XGBoost, and LightGBM) is trained on each feature branch, and stable probability outputs are obtained via stratified K-fold out-of-fold training, probability calibration, and a quantile-based threshold search. Decision-level fusion is then performed by stacking, where logistic regression, XGBoost, and LightGBM serve as meta-learners over the out-of-fold probabilities of the selected top-K base learners. Experiments on two public benchmarks (MVTec AD and BTAD) show that the proposed method substantially improves the best PCA-based single model, achieving relative F1_score gains of approximately 31% (MVTec AD) and 26% (BTAD), with maximum AUC values of about 0.91 and 0.96, respectively, under comparable inference complexity. Overall, the results demonstrate that combining high-quality handcrafted features with supervised ensemble fusion provides a practical and interpretable alternative/complement to heavier deep models for resource-constrained industrial anomaly detection, and future work will explore more category-adaptive decision strategies to further enhance robustness on challenging classes. Full article

Background: Chronological age inadequately captures biological vulnerability among surgical patients. Frailty and muscle strength reflect physiological reserve, yet their combined contribution to postoperative length of stay (LOS) remains insufficiently explored. Methods: We conducted a prospective multicenter observational cohort study including 223 adults undergoing elective abdominal surgery. Frailty was assessed using the Fried phenotype, and admission handgrip strength (HGS) was measured with a calibrated dynamometer. Prolonged LOS was defined as >10 days (75th percentile) and also analyzed continuously using ln(LOS + 1). Multivariable logistic and linear regression models adjusted for age, sex, frailty status, and surgical indication. Patients were additionally stratified into four physiological reserve phenotypes combining frailty and HGS. Results: LOS ranged from 0 to 68 days; a total of 48 patients (21.6%) experienced prolonged hospitalization. In multivariable logistic regression, frailty (adjusted OR 3.12, 95% CI 1.72–5.67) and oncologic surgery (adjusted OR 7.63, 95% CI 3.12–18.65) were independently associated with prolonged LOS, whereas chronological age was not. Female sex was associated with lower odds of prolonged LOS (adjusted OR 0.39, 95% CI 0.18–0.87). Similar associations were observed when LOS was analyzed continuously. Physiological reserve phenotyping revealed graded LOS distributions: Fit–Strong patients had the shortest stays (mean 5.5 ± 4.3 days), while Frail–Weak patients experienced the longest and most variable hospitalization. Conclusions: Postoperative LOS clusters according to multidimensional physiological reserve rather than chronological age. Integrating frailty and muscle strength identifies clinically meaningful phenotypes that may improve perioperative risk stratification beyond age-based approaches and inform personalized perioperative planning, resource allocation, and patient-centered decision-making across heterogeneous surgical populations in worldwide settings. Full article

Leaf area index (LAI) is a key indicator of crop growth and development and is widely used in both agricultural research and precision farming applications. PlanetScope imagery is generally used for monitoring crop growth due to its high revisit frequency, broad spatial coverage, and cost-effective access to consistent high-resolution multispectral data. Therefore, we developed regression models to estimate peanut LAI, combining PlanetScope spectral bands and vegetation indices (VIs). Specifically, we compared the performance of random forest (RF), eXtreme Gradient Boosting (XGBoost), and Partial Least Squares Regression (PLSR) regression algorithms for peanut LAI estimation. Our results showed that most of the VIs exhibited strong relationships with LAI. Thirteen VIs were individually evaluated for estimating LAI using the aforementioned algorithms, and our results showed that the best single predictors of LAI are: TSAVI (RF: R² = 0.87, RMSE = 0.83 m²/m², RRMSE = 24.20%; XGBoost: R² = 0.77, RMSE = 0.95 m²/m², RRMSE = 27.96%); and RTVIcore (PLSR: R² = 0.68, RMSE = 1.12 m²/m², RRMSE = 32.88%). The top six ranked VIs were used to calibrate the RF, XGBoost, and PLSR algorithms. Model validation indicated that RF achieved the highest accuracy (R² = 0.844, RMSE = 0.858 m²/m², RRMSE = 25.17%), followed by XGBoost (R² = 0.808, RMSE = 0.92 m²/m², RRMSE = 26.99%), whereas PLSR showed comparatively lower performance (R² = 0.76, RMSE = 0.983 m²/m², RRMSE = 28.85%). Further results showed that PlanetScope VIs provided superior model accuracy in estimating peanut LAI compared to the use of spectral bands alone. Additionally, integrating spectral bands with VIs reduced LAI estimation accuracy, underscoring the importance of selecting predictor variables in ensuring optimal model performance. Overall, the presented results are significant for future crop monitoring using RF to reduce overreliance on multiple models for peanut LAI estimation. Full article

Purpose: This study aimed to investigate the association between lactate dehydrogenase-to-albumin ratio (LAR) and the clinical characteristics and overall survival (OS) of patients with neuroblastoma (NB). Methods: We conducted a retrospective data analysis of 443 patients diagnosed with neuroblastoma. The optimal cut-off value for the LAR was determined using receiver operating characteristic (ROC) curves. We utilized Kaplan–Meier curves and Cox regression analysis to evaluate the relationship between LAR and OS. Independent factors identified through multivariate analysis were employed to construct a nomogram. The performance of the nomogram model was assessed using calibration curves, ROC curves, concordance index (C-index), and decision curve analysis (DCA). Results: The 2-year time-dependent ROC curve indicated that the optimal cut-off value for the LAR was 21.814. Kaplan–Meier survival curve analysis revealed that the prognosis for the high LAR group was significantly worse than that for the low LAR group. Results from multivariate Cox analysis identified INSS stage, bone metastasis, MYCN, and LAR as independent prognostic factors for OS. A nomogram for predicting the prognosis of NB was established based on multivariate Cox regression analysis. Internal validation through the Bootstrap method revealed that the nomogram’s C-index was 0.727. Both the calibration curve and ROC curve suggested that the model possessed significant predictive potential. DCA further demonstrated that the nomogram model exhibited substantial clinical applicability. Conclusions: LAR served as an aussichtsreich prognostic indicator for neuroblastoma, and the nomogram model based on LAR can predict the OS of patients with this condition. Full article

Performance diagnostics in alpine skiing increasingly rely on integrated biomechanical and kinematic assessments to support technique optimization under real training conditions; however, many existing approaches address trajectory geometry or biomechanical variables separately, limiting their explanatory power. This study evaluates an integrated analysis framework combining OptiPath, an AI-assisted video-based trajectory analysis tool, with XSensDOT wearable inertial sensors to identify technical inefficiencies during giant slalom skiing. Thirty competitive youth athletes (n = 30; 14–16 years) performed controlled runs with predefined lateral offsets from the gates, enabling systematic examination of the relationship between spatial trajectory deviations, biomechanical execution, and performance outcomes. Skier trajectories were extracted using computer vision-based methods, while lower-limb kinematics, trunk motion, and tri-axial acceleration were recorded using inertial measurement units. Deviations from mathematically defined ideal trajectories were quantified through regression-based calibration and arc-based modeling. The results show that although OptiPath reliably detected trajectory variations, shorter skiing paths did not consistently produce faster run times. Instead, superior performance was associated with more efficient biomechanical execution, reflected by coordinated trunk–lower limb motion, controlled vertical loading, reduced lateral corrections, and higher forward acceleration, even when longer trajectories were followed. These findings indicate that trajectory geometry alone is insufficient to explain performance outcomes and support the integration of wearable biomechanics with trajectory modeling as a practical, low-cost, and field-deployable tool for alpine skiing performance diagnostics. Full article

Background: Visceral fat plays a central role in cardiometabolic risk among people with type 2 diabetes mellitus (T2DM), yet its assessment in routine clinical practice remains largely dependent on imaging techniques or indirect anthropometric measures. Identifying accessible blood-based markers that reflect visceral adiposity may facilitate improved phenotyping in this population. This study aimed to investigate whether circulating coiled-coil domain–containing protein 3 (CCDC3) reflects visceral fat accumulation in adults with T2DM. Methods: Public RNA-sequencing datasets and human adipose tissue samples were analyzed to identify CCDC3 as a visceral fat–enriched secretory gene. In this cross-sectional study of 160 adults with T2DM undergoing dual-energy X-ray absorptiometry, plasma CCDC3 was measured by ELISA. Associations between plasma CCDC3 and visceral fat area (VFA) were examined using multivariable regression. Logistic regression models for abdominal obesity (VFA ≥ 100 cm²), with and without CCDC3, were evaluated using receiver operating characteristic (ROC) analysis, calibration curves, decision curve analysis (DCA), and Shapley additive explanations (SHAP). Results: Circulating CCDC3 levels were positively associated with VFA (β = 3.11, p < 0.001), independent of demographic and metabolic factors. Incorporating CCDC3 into the baseline model significantly improved discrimination of abdominal obesity (AUC 0.820 vs. 0.663; p = 0.009). Calibration curves and DCA supported better model fit and higher net clinical benefit with CCDC3. SHAP analysis showed that CCDC3 contributed the greatest incremental importance beyond waist circumference, sex, and age. Conclusions: Circulating CCDC3 may serve as a blood-based biomarker reflecting visceral adiposity in adults with T2DM and provides complementary information beyond traditional anthropometric measures. Full article

The rapid deployment of photovoltaic generation increases uncertainty in power-system operation and strengthens the need for ultra-short-term forecasts with reliable uncertainty estimates. Point-forecasting approaches alone are often insufficient for dispatch and reserve decisions because they do not quantify risk. This study investigates probabilistic forecasting of short-horizon solar generation using quantile regression on a public dataset of solar output and meteorological variables. This study proposes a hybrid attention–convolution model that combines an attention-based encoder to capture long-range temporal dependencies with a causal temporal convolution module that extracts fast local fluctuations using only past information, preventing information leakage. The two representations are fused and decoded jointly across multiple future horizons to produce consistent quantile trajectories. Experiments against representative machine-learning and deep-learning baselines show improved probabilistic accuracy and competitive central forecasts, while illustrating an important sharpness–calibration trade-off relevant to risk-aware grid operation. Key novelties include a multi-horizon quantile formulation at 15 min resolution for one-hour-ahead PV increments, a HybridCNN–STTransformer that fuses causal temporal convolutions with Transformer attention, and a horizon-token decoder that models inter-horizon dependencies to produce consistent multi-step quantile trajectories; reliability/sharpness diagnostics and post hoc calibration are discussed for operational risk-aware use. Full article

Accurate braking-distance prediction for heavy-duty multi-axle trucks remains challenging due to the large gross vehicle weight, tandem-axle interactions, and strong transient load transfer during emergency braking. Recent studies on tire–road friction estimation, commercial-vehicle braking control (EBS/AEBS), and weigh-in-motion (WIM) sensing have highlighted that unmeasured vertical-load dynamics and time-varying friction are key sources of prediction uncertainty. To address these limitations, this study proposes an integrated sensing–simulation–AI framework that combines real-time axle-load estimation, full-scale robotic braking tests, fused road-friction sensing, and physics-consistent machine-learning modeling. A micro-electro-mechanical systems (MEMS)-based load-angle sensor was installed on the leaf-spring panel linking tandem axles, enabling the continuous estimation of dynamic vertical loads via a polynomial calibration model. Full-scale on-road braking tests were conducted at 40–60 km/h under systematically varied payloads (0–15.5 t) using an actuator-based braking robot to eliminate driver variability. A forward-looking optical friction module was synchronized with dynamic axle-load estimates and deceleration signals, and additional scenarios generated in a commercial ASM environment expanded the operational domain across a broader range of friction, grade, and loading conditions. A gradient-boosting regression model trained on the hybrid dataset reproduced measured stopping distances with a mean absolute error (MAE) of 1.58 m and a mean absolute percentage error (MAPE) of 2.46%, with most predictions falling within ±5 m across all test conditions. The results indicate that incorporating real-time dynamic axle-load sensing together with fused friction estimation improves braking-distance prediction compared with static-load assumptions and purely kinematic formulations. The proposed load-aware framework provides a scalable basis for advanced driver-assistance functions, autonomous emergency braking for heavy trucks, and infrastructure-integrated freight safety management. All full-scale braking tests were carried out at approximately 60% of the nominal service-brake pressure, representing non-panic but moderately severe braking conditions, and the proposed model is designed to accurately predict the resulting stopping distance under this prescribed braking regime rather than to minimize the absolute stopping distance itself. Full article

This paper examines the regressive nature of the value-added tax and proposes an integrated framework combining a uniform value-added tax rate with progressive, digitally administered rebates. The model was performed using household- and firm-level microsimulations with Monte Carlo methods. It demonstrates that equity can be reached without revenue neutrality being undermined. Simulation results for a calibrated 2024–2025 economy show the proposed rebate structure reduces the effective tax burden on the lowest income quintile from 13.5% to 5.4% of income, delivering a net cash benefit of USD 786.88 and a welfare gain of 6.10%. The policy is projected to generate a robust average VAT revenue of USD 17.44 million, with a 97.8% probability of a positive fiscal impact, while reducing the poverty rate by 2.6% and lowering inequality (Gini coefficient of utility to 0.199). The outcomes present a welfare gain for the poor, a small firm-level effect, and a decrease in poverty and inequality. The results suggest a feasible policy route towards a more equitable tax system, thus promoting indirectly to the United Nations Sustainable Development Goals (SDGs), specifically SDG 8 (decent work and economic growth) and SDG 10 (reduced inequalities). 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

Global food security faces escalating threats from climate variability and resource constraints. Accurate crop yield forecasting is essential; however, existing methods frequently overlook complex spatial dependencies driven by climate teleconnections, such as the ENSO, and lacks rigorous uncertainty quantification. This paper presents HSE-GNN-CP, a novel framework integrating heterogeneous stacked ensembles, graph neural networks (GNNs), and conformal prediction (CP). Domain-specific features are engineered, including growing degree days and climate suitability scores, and explicitly model spatial patterns via rainfall correlation graphs. The ensemble combines random forest and gradient boosting learners with bootstrap aggregation, while GNNs encode inter-regional climate dependencies. Conformalized quantile regression ensures statistically valid prediction intervals. Evaluated on a global dataset spanning 15 countries and six major crops from 1990 to 2023, the framework achieves an R² of 0.9594 and an RMSE of 4882 hg/ha. Crucially, it delivers calibrated 80% prediction intervals with 80.72% empirical coverage, significantly outperforming uncalibrated baselines at 40.03%. SHAP analysis identifies crop type and rainfall as dominant predictors, while the integrated drought classifier achieves perfect accuracy. These contributions advance agricultural AI by merging robust ensemble learning with explicit teleconnection modeling and trustworthy uncertainty quantification. Full article

The rapid expansion of small and medium enterprise (SME) lending has intensified the need for accurate and interpretable credit risk forecasting. Financial institutions must anticipate potential business loan delinquency to maintain portfolio stability and meet regulatory standards. This study proposes an interpretable multi-model framework that integrates statistical (correlation screening and ordinary least squares regression), probabilistic (Gaussian Naïve Bayes), and classical time-series (SARIMA) methods to balance explanatory insight and predictive accuracy in delinquency forecasting. Ordinary least squares regression is used to quantify the direction and strength of each driver and yields statistically significant coefficients (β ≈ 1.336 for the overdue 15+ days bucket, p < 10⁻²²). The Naïve Bayes classifier provides a probabilistic early-warning signal with an out-of-sample accuracy of 55%, precision of 43%, recall of 75%, and ROC AUC of 0.371. Finally, a seasonal ARIMA model fitted on the selected regressors achieves a mean absolute percentage error (MAPE) of 7.6% and an out-of-sample R² of 0.49, demonstrating competitive forecasting performance while maintaining interpretability. The results show that the framework offers actionable insights for risk managers by identifying key risk drivers, providing probabilistic alarms, and generating calibrated point forecasts. The proposed approach contributes to the development of intelligent and explainable forecasting and control systems for modern financial institutions. Full article

Large civil infrastructure, such as nuclear power plant containment vessels, is predominantly constructed using prestressed concrete (PSC) or reinforced concrete (RC). Previous experimental studies investigated the internal blast responses of reduced-scale open-ended reinforced concrete containment vessel (RCCV) and prestressed concrete containment vessel (PCCV), providing insight into displacement-based structural behavior. However, these studies were limited by the inability to directly measure internally reflected wall pressures and by the lack of experimental data for enclosed boundary conditions. In this study, a displacement-calibrated LS-DYNA simulation framework is developed to extend prior experimental findings to both open-ended and enclosed RCCV and PCCV configurations. An internal detonation of ammonium nitrate–fuel oil (ANFO) is simulated at the center of a cylindrical vessel. The simulation models are calibrated using reduced-scale open-ended experimental displacement time histories. Simulation results are post-processed to construct force–displacement relationships based on discrete load–displacement points across charge levels and their bilinear regression. Using the resulting stiffness indices and a stiffness-based scaling procedure, failure-inducing internal blast loads are estimated for real-scale vessels under conditions where direct internal pressure measurement is not feasible. The proposed framework enables response-based assessment of semi-confined internal explosions and supports model-informed safety evaluation of containment-type structures. Full article

Sustainable management of indoor and outdoor air quality is essential for protecting public health, enhancing well-being, and supporting resilient urban environments. Low-cost air quality sensors enable continuous, real-time monitoring of key pollutants and, when combined with data analytics, provide scalable and cost-effective insights for smart building operation and environmental decision-making. This pilot study evaluates an indoor–outdoor air quality monitoring system deployed at the Faculty of Electrical Engineering and Information Technologies in Skopje, with a focus on: (i) PM2.5 and PM10 concentrations and their relationship with meteorological conditions and human occupancy; (ii) sensor responsiveness and reliability in an educational setting; and (iii) implications for sustainable building operation. From January to March 2025, two indoor sensors (a classroom and a faculty hall) and two outdoor rooftop sensors continuously measured PM2.5 and PM10 at one-minute intervals. All sensors were calibrated against a reference instrument prior to deployment, while meteorological data were obtained from a nearby station. Time-series analysis, Pearson correlation, and multiple regression were applied. Indoor particulate levels varied strongly with occupancy and ventilation status, whereas outdoor concentrations showed weak to moderate correlations with meteorological variables, particularly atmospheric pressure. Moderate correlations between indoor and outdoor PM suggest partial pollutant infiltration. Overall, this pilot study demonstrates the feasibility of low-cost sensors for long-term monitoring in educational buildings and highlights the need for adaptive, context-aware ventilation strategies to reduce indoor exposure. Full article