Search Results (10,405)

Electroluminescence (EL) imaging is widely used for non-destructive inspection of photovoltaic (PV) cells; however, the low contrast of grayscale EL images limits the performance of automated defect detection methods. This manuscript proposes a defect-aware EL image classification framework that enhances defect visibility through local contrast enhancement and physically motivated RGB false-color mapping. Instead of simple channel replication, grayscale intensities are segmented into defect-related ranges and encoded to emphasize cracks, inactive regions, healthy silicon emission, and conductive pathways. The approach is evaluated on the public ELPV benchmark dataset proposing ResNet–50, EfficientNet–B0, and EfficientNet–B3 architectures at two input resolutions. The proposed representation consistently improves defect discrimination and achieves a maximum classification accuracy, outperforming previously reported CNN-based results on the same dataset. Notably, comparable accuracy is obtained at lower resolution, significantly reducing computational cost and inference time, which supports deployment with cheaper sensors and faster inspection pipelines. Class imbalance is addressed using focal loss, class weighting, and threshold calibration without artificial resampling, preserving realistic operating conditions. The results confirm that combining defect-aware RGB representation with resolution-efficient learning provides an accurate and computationally practical solution for EL-based PV defect detection. Full article

Land subsidence induced by excessive groundwater abstraction has emerged as a major geo-environmental hazard in arid oasis regions, calling for reproducible methods to quantitatively assess the abstraction-reduction–subsidence response and to support zoned management. This study integrates Sentinel-1A PS-InSAR deformation data with groundwater-level measurements to develop and calibrate a MODFLOW-SUB model that couples three-dimensional groundwater flow and one-dimensional skeletal compaction. The InSAR deformation field is used to constrain the conceptual model and key parameters. Four abstraction-reduction scenarios (20%, 40%, 60%, and 80%) are designed to characterize response curves using indicators such as maximum cumulative subsidence, annual subsidence rate, and the area exceeding specified thresholds. In addition, a multi-criteria composite index integrating driving forces, geological susceptibility, and exposure is applied for hazard zoning and scenario comparison. The results show that PS-InSAR constraints improve the spatial agreement of the simulations. The time-series RMSE between simulated and InSAR-derived deformation is approximately 20 mm, and the end-of-period cumulative subsidence error is within 10 mm. From 2019 to 2020, the maximum cumulative subsidence reached 166 mm, and the peak subsidence rate reached 101 mm/a. A clear lag between groundwater-level fluctuations and subsidence is observed, with the maximum correlation occurring at ~35 days for ACJ-1 and ~59–83 days for ACJ-2. This spatial variability is associated with the thickness and permeability of clay layers. Forecasts for 2021–2028 indicate that, under business-as-usual abstraction, maximum subsidence may reach 695 mm. Across scenarios, subsidence mitigation exhibits diminishing marginal returns with increasing abstraction reduction. Under the adopted model settings, a 20% reduction in abstraction yields substantial decreases in maximum subsidence and high-hazard area, representing a practical trade-off between mitigation benefits and water-use costs. Overall, the integrated workflow of monitoring, inversion, coupled modeling, scenario analysis, and zoning, together with the resulting zoned management recommendations, provides decision support for land-subsidence mitigation and water-allocation planning in arid oasis regions. Full article

Lonicera caerulea L. (blue honeysuckle) is rich in antioxidant polyphenols, and rapid and accurate determination of its polyphenol content is of great significance for functional food quality control. This study proposed a hybrid variable selection strategy designed for high-dimensional small-sample scenarios and developed a quantitative prediction model for polyphenol content based on mid-infrared (MIR) spectroscopy. A total of 191 Lonicera caerulea samples were collected from Northeast China, and 7468-dimensional spectral data were acquired using a Fourier transform infrared spectrometer. Polyphenol reference values were determined by the Folin–Ciocalteu method. Samples were divided into calibration (n = 152) and prediction (n = 39) sets using the SPXY algorithm. Among the 10 preprocessing methods evaluated, MSC combined with Savitzky–Golay first derivative achieved the best performance and was therefore used for subsequent modeling. The proposed hybrid variable selection method (VIP1.0∩RFR30%) intersected PLS variable importance in projection (VIP ≥ 1.0) with the top 30% important variables from random forest regression, selecting 984 key wavelengths and achieving 86.8% dimensionality reduction. A three-stage hyperparameter tuning strategy was implemented across four models (PLS, RFR, SVR, and XGBoost) to validate feature stability and control overfitting. The optimized XGBoost model achieved excellent performance on the independent test set ($R^2$ = 0.92, RMSE = 0.098, RPD = 3.47). Compared with the classical CARS method ($R^2$ = 0.78, RPD = 2.14), $R^2$ improved by 16.3% and RPD improved by 55.2%. The results demonstrate that the proposed hybrid variable selection strategy can effectively address the challenges of high-dimensional MIR spectral data in small-sample modeling, providing a reliable tool for rapid and non-destructive quantitative analysis of polyphenols in Lonicera caerulea. Full article

Accurate multi-modal traffic demand forecasting is key to optimizing intelligent transportation systems (ITSs). To overcome the shortcomings of existing methods in capturing dynamic high-order correlations between heterogeneous spatial units and decoupling intra- and inter-mode dependencies at multiple time scales, this paper proposes a Dynamic Multi-Relation Learning with Multi-Scale Hypergraph Transformer method (MST-Hype Trans). The model integrates three novel modules. Firstly, the Multi-Scale Temporal Hypergraph Convolutional Network (MSTHCN) achieves collaborative decoupling and captures periodic and cross-modal temporal interactions of transportation demand at multiple granularities, such as time, day, and week, by constructing a multi-scale temporal hypergraph. Secondly, the Dynamic Multi-Relationship Spatial Hypergraph Network (DMRSHN) innovatively integrates geographic proximity, passenger flow similarity, and transportation connectivity to construct structural hyperedges and combines KNN and K-means algorithms to generate dynamic hyperedges, thereby accurately modeling the high-order spatial correlations of dynamic evolution between heterogeneous nodes. Finally, the Conditional Meta Attention Gated Fusion Network (CMAGFN), as a lightweight meta network, introduces a gate control mechanism based on multi-head cross-attention. It can dynamically generate node features based on real-time traffic context and adaptively calibrate the fusion weights of multi-source information, achieving optimal prediction decisions for scene perception. Experiments on three real-world datasets (NYC-Taxi, -Bike, and -Subway) demonstrate that MST-Hyper Trans achieves an average reduction of 7.6% in RMSE and 9.2% in MAE across all modes compared to the strongest baseline, while maintaining interpretability of spatiotemporal interactions. This study not only provides good model interpretability but also offers a reliable solution for multi-modal traffic collaborative management. Full article

To address the lack of contact and breakage parameters in the discrete element method (DEM) simulation of potato seed cutting and sorting processes, this study took the ‘Atlantic’ potato seed as the research object and constructed a crushable potato model using EDEM. Through physical experiments, the mean average diameter, moisture content, density, Poisson’s ratio, and elastic modulus were measured. The coefficients of collision restitution, static friction, and rolling friction between the potato seed and the Q235 steel plate were determined as 0.576, 0.559, and 0.073, respectively. Using the actual repose angle of 22.89° as the response target, and combining the steepest ascent test with the Box–Behnken design, the non-cohesive contact parameters between potato seed particles were calibrated. The resulting coefficients of collision restitution, static friction, and rolling friction between particles were determined as 0.404, 0.412, and 0.0156, respectively. Finally, based on physical shear tests (maximum shear force 23.56 N), significant influencing factors were identified through Plackett–Burman screening as the bonding radius ratio r and the normal stiffness per unit area Kn. Using the steepest ascent test and the Box–Behnken response surface method, the key bonding parameters of the Bonding V2 model were calibrated as follows: r = 1.098, K_n = 8.597 × 10⁷ N·mm⁻³, tangential stiffness per unit area K_t = 3.250 × 10⁶ N·mm⁻³, critical compressive stress σ_n = 5.500 × 10⁵ Pa, and shear strength τ_t = 3.000 × 10⁴ Pa. The relative error between the simulated and actual maximum shear forces was 0.89%, which is small. The calibrated flexible model accurately represents the physical characteristics of potato seeds and provides a reliable reference for the design of mechanized potato seed cutting and sorting equipment. Full article

Urban air quality assessment is central to environmental sustainability and public health management. This study presents a structured comparative evaluation of Random Forest (RF), Support Vector Machine (SVM), LSTM, and Bi-LSTM models for pollutant-driven air quality classification under the Indian National Air Quality Index (NAQI) framework defined by CPCB guidelines. To provide a fair comparison, multi-pollutant data of Indian urban monitoring stations were preprocessed, and the class-balancing protocol and validation protocol were combined. RF had highest total accuracy (0.9971) in the held-out set, with Bi-LSTM (0.9615), LSTM (0.9495), and SVM (0.9442) coming next. Although ensemble methods proved to be very separable in line with the threshold-based NAQI structure, Bi-LSTM was more stable when it came to boundary-sensitive switches among the adjacent severity classes. Calibration analysis (multiclass Brier score: 0.08) showed consistent probabilistic behavior and interpretation, and using SHAP showed physically significant pollutant driving factors. The results explain the appropriateness of comparative models in organized AQI classification and present a reproducible assessment framework for the NAQI framework. Full article

Opioid-related iatrogenic harms, including opioid use disorder, overdose, and opioid-induced respiratory depression, constitute a major patient safety challenge. Although clinicians document key safety signals in unstructured clinical narratives, many of these indicators are not readily captured by conventional surveillance approaches that rely on structured administrative data. This clinically focused narrative review synthesizes 47 empirical studies published between 2009 and 2025 that applied artificial intelligence (AI) methods to identify opioid-related harms from clinical text and to address the resulting ascertainment gap. Across studies, administrative coding systems, including ICD-10, often under-ascertain opioid-related events, whereas text-based AI can identify additional cases and contextual details often documented primarily in narrative records, such as fluctuating mental status, suspected drug causality, and responses to naloxone. Methodologically, the literature has progressed from interpretable rule-based lexicons to machine learning and deep learning models and, more recently, to transformer-based approaches, including large language models (LLMs) for classification and schema-driven extraction. Rule-based systems established the feasibility of transparent surveillance and frequently recovered clinically documented cases missed by billing codes. Subsequent supervised and deep learning approaches expanded scalability and, in a smaller subset of studies, were integrated into electronic health record workflows with operational metrics reported. More recent transformer- and LLM-based studies emphasize richer extraction schemas and benchmark development, including characterization of overdose context and intentionality and identification of potential prodromal neurocognitive signals, although external validation, calibration, and prospective outcome evaluation remain inconsistently reported. Given that the evidence base is predominantly retrospective and that clinical workflow studies remain comparatively few, a pragmatic near-term clinical role is to provide detection-to-triage decision support rather than autonomous diagnosis, in which systems surface candidate cases with reviewable evidence for clinician adjudication. Future progress will require greater standardization of phenotype definitions, routine equity auditing and subgroup reporting, stronger external validation and calibration at operational thresholds, and a shift from retrospective discrimination metrics toward prospective assessments of the clinical workflow impact, clinical utility, and patient-centered outcomes. Full article

Background/Objectives: To investigate and develop a non-invasive parametric radiomics model derived from dynamic contrast-enhanced MRI (DCE-MRI) time-intensity curve (TIC) kinetics for predicting breast cancer molecular subtypes (HR+/HER2−, HER2+ and triple-negative breast cancer). Methods: This multicenter retrospective study enrolled 935 female patients with histologically confirmed breast cancer who underwent pretreatment breast DCE-MRI from August 2017 to July 2022. Based on the wash-in rate (WIR) and the area under the TIC, the original multiphase DCE-MRI images were converted into two types of parametric images. Radiomics features were extracted from TIC-WIR and TIC-Area images and analyzed using low variance filtering, the elimination of highly correlated features, and the least absolute shrinkage and selection operator regression. The categorical boosting algorithm was employed to develop multiclass prediction models for breast cancer molecular subtyping. A TIC-Combined model was further established by integrating the calibrated probability outputs of the TIC-WIR and TIC-Area models using a decision-level fusion strategy. The discrimination, calibration, and interpretability of the models were evaluated in the study datasets. Results: The TIC-Combined model achieved superior predictive performance in both the internal validation set (micro-average AUC: 0.79, macro-average AUC: 0.77) and the external validation set (micro-average AUC: 0.77, macro-average AUC: 0.75). For subtype-specific classification by the TIC-Combined model, the highest one-vs-rest AUCs were 0.81 for triple-negative breast cancer in the internal validation set and 0.76 for HER2+ breast cancer in the external validation set. The TIC-Combined model also showed good calibration and high interpretability which ensured reliable predictions and provided clear insights into feature importance. Conclusions: Interpretable parametric radiomics from TIC-derived parametric maps links kinetic features to molecular phenotypes, enabling accurate and non-invasive classification of breast cancer molecular subtypes. Full article

Waterfront recreational spaces, as key urban ecological resources, are distinctive in their scarcity and ecological fragility. Their sustainable revitalization requires evidence-based spatial planning and design. The analysis of the vitality of waterfront recreational spaces, which are characterized by the interaction between space and experience, essentially explores how human, water, and the city can coexist and thrive together. Based on the dual characteristics of vitality, this study presents a space–experience interactive evaluation system for waterfront recreational places that incorporates multi-source data. The vitality evaluation results can then be cross-validated with intuitive representations of vitality quantified using pedestrian flow data. Furthermore, this can be used to accurately calibrate the vitality gradient, identify and analyze the anomalous units, and provide insight into influencing factors and underlying mechanisms of vitality. The empirical investigation of the waterfront recreational area of Suzhou Jinji Lake Scenic Area (JLSA) demonstrates that this method can accurately identify spatial vitality distributions and effectively characterize the key elements of vitality zones at different levels. It can precisely decode the vitality of waterfront recreational spaces, providing fresh perspectives on understanding the space–experience interaction in waterfront recreational spaces and directing actions for enhancing vitality. In addition to serving as a supplement to existing research, it provides a flexible, scalable evaluation framework for a variety of waterfront contexts, supports the implementation of human-centered urban design, and offers theoretical and practical support for the sustainable development of waterfront areas. Full article

In mine ventilation network calibration, sparse and inconsistent airflow measurements often lead to infeasibility in traditional optimization models. To overcome this challenge, this paper proposes a nonlinear programming calibration model incorporating slack variables. The model treats aerodynamic resistance corrections, airflow adjustments, unknown airflows, and resistance lower-bound slack variables as decision variables. The objective function is formulated to minimize the weighted sum of squares of resistance corrections, while penalty terms account for airflow adjustments and slack variables. Constraints integrate Kirchhoff’s laws with relaxed inequality constraints for resistance lower bounds. A calibration tool integrated via the ObjectARX interface was developed using C++, utilizing the Sequential Quadratic Programming (SQP) algorithm for the solution. The method was validated via a case study of a network comprising 39 branches and 16 measured airflows, optimized under five distinct initial conditions. Results demonstrate that the inclusion of slack variables mathematically guarantees the existence of feasible solutions. With a resistance correction weight of 10⁻² and a penalty coefficient of 10⁵, the model applies only minimal necessary corrections to handle overly tight constraints or data conflicts. The SQP algorithm exhibits superior global convergence, consistently iterating to optimal solutions that satisfy network balance laws regardless of initial values. This approach effectively resolves the infeasibility and data conflict issues inherent in traditional methods, demonstrating significant robustness and practical engineering utility. Full article

As global aquaculture continues to expand, there is increasing interest in sustainable and non-invasive tools for monitoring fish growth. Nile tilapia (Oreochromis niloticus) is one of the most farmed species worldwide. Its biomass estimation often relies on manual sampling or stereo-camera systems limited by water turbidity. This study establishes a robust relationship between lateral target strength (TS) and the total length (TL) and weight (W) of Nile tilapia using a cost-effective 201 kHz single-beam echosounder. Measurements were conducted with free-swimming fish in a controlled pond environment (TL range, 13–44 cm). The results show a strong linear correlation between acoustic and biometric data. Specifically, the relationship for mean TS was defined as TS_mean = 20.4log(TL) − 68.8 (R² = 0.93) and TS_mean = 6.3log(W) − 55.4 (R² = 0.96), proving the system’s accuracy for biomass estimation. Furthermore, the Method of Fundamental Solutions (MFS) was employed for numerical validation based on X-ray morphometry of the swim bladder. Very good agreement was observed between experimental data and numerical simulations, reinforcing the validity of the acoustic models despite the inherent complexity of biological targets. These findings demonstrate that calibrated single-beam acoustic systems provide a viable, non-intrusive tool for real-time monitoring in aquaculture ponds. Full article

The growing global demand for mineral resources is challenging mining operations to maintain productivity while processing lower-grade ores and increasingly complex deposits. This study presents an integrated framework that leverages machine learning (ML) and high-fidelity simulation to model and support scenario-based decision-making for the blasting–crushing–SAG (Semi-Autogenous Grindin) milling chain using a calibrated flowsheet. Using publicly available data from the Barrick Cortez Mine (Nevada, USA), more than three million operational scenarios were generated using the Integrated Extraction Simulator (IES) to capture system variability and sensitivity. Machine learning meta-models, built using Random Forest and XGBoost methods, were trained on the simulated data and achieved coefficients of determination (R²) exceeding 0.90 across all key outputs, including P20, P50, P80, and mass flow rates at different operational stages. The meta-models accurately reproduced plant-scale behaviour while reducing computational requirements by several orders of magnitude compared with full-scale simulations. SHapley Additive exPlanations (SHAP) analysis revealed that blast-hole diameter, explosive energy parameters, screen cut-size, crusher feed characteristics, and SAG mill operating conditions are the dominant factors impacting downstream particle size distributions. The proposed framework enables near-real-time evaluation of “what-if” operational scenarios and provides transparent, quantitative decision-support for integrated mine-to-mill optimisation. Full article

In the cold and arid regions of northern China, efficient water and nitrogen (N) management is critical for the sustainable production of leafy vegetables. Simplified models that estimate crop N and water transpiration demands using simple inputs based on climate parameters become an important method for making precise suggestions on N and irrigation application at a regional scale. This study developed and validated a regionally adapted version of the VegSyst model, named VegSyst-CH, based on a multi-year open-field experiment from 2021 to 2023. Model parameters were calibrated using data from the 2021 growing season and validated with independent datasets from 2022 and 2023. A critical N concentration (CNC) curve was established to describe the relationship between biomass accumulation and N content. VegSyst-CH, with a radiation use efficiency of 1.94 g MJ⁻¹, demonstrated high simulation accuracy for crop growth. The model showed a good predictive performance of N uptake under medium (N1) and high (N2) N treatments, with coefficients of determination (R²) above 0.80 across years and normalized root mean square error (NRMSE) values generally below 30%. The VegSyst-CH model also showed high accuracy in simulating crop evapotranspiration (ETc) over three consecutive growing seasons (2021–2023), with the dynamic trends of cumulative ETc closely aligning with measured values and the coefficients of determination (R²) consistently exceeding 0.90. These results validate the model’s robustness and applicability across different years. In conclusion, the VegSyst-CH model has strong spatiotemporal regulation capacity and climatic responsiveness, offering a robust decision support tool for precision fertilization and irrigation in open-field lettuce production in cold and arid regions. Full article

Objectives: This study aims to evaluate whether changes in perfusion index (PI) after the first deflation of the blood pressure cuff during remote ischemic conditioning (RIC) are associated with passive leg raising (PLR)-induced changes in stroke volume. In addition, we compared PI changes after cuff deflation during RIC between critically ill patients and healthy controls. Methods: This prospective, single-center study was conducted in a mixed ICU at a tertiary teaching hospital. Patients aged >18 years admitted to the ICU, monitored using calibrated pulse contour analysis, and scheduled for a PLR test as decided by the attending physicians were included. The PI was measured after blood pressure cuff deflations during RIC (3 cycles of brachial cuff inflation to 200 mmHg for 5 min, followed by instantaneous deflation to 0 mmHg for another 5 min) in the supine position after PLR. Preload responsiveness was defined as a ≥10% increase in the stroke volume index (SVI) during PLR. Data were compared with a healthy control group. Results: Thirty-three patients were included (median age 62; 45% in shock; 55% mechanically ventilated). When comparing critically ill patients with healthy volunteers, the maximum PI change (dPImax) and the time to reach it were higher in critically ill patients after the first and second cuff deflations (p < 0.05). However, after the third deflation, the difference was no longer significant. Following the first deflation, dPImax was significantly correlated with SVI changes during PLR (r = 0.63, p < 0.001). After the cuff was first deflated, we detected a PI cutoff with a positive SVI response (≥10%) during PLR, with a sensitivity of 64% and a specificity of 94% (area under the receiver operating characteristic curve 0.752; 95% CI, 0.564–0.940; p = 0.008). Conclusions: The maximum change in perfusion index following brachial blood pressure cuff deflation after five minutes of inflation may serve as a promising noninvasive bedside indicator of preload responsiveness in critically ill patients. Additionally, the observed normalization of PI kinetics during RIC suggests possible acute modulation of vascular reactivity, though further research is needed to confirm an association between PI changes and endothelial function. Full article

This study investigates the impact of occupational noise on the physical and mental health of 50 water pumping station operators in Lebanon. The research aimed to quantify noise exposure, assess its effects on hearing and psychological well-being, and identify contributing factors. To achieve this, this study employed several evaluation methods. Noise exposure was measured using a calibrated sound level meter to determine the average A-weighted sound pressure levels (dBA) at 52 stations, which were then compared to the 85 dBA recommended limit from the National Institute for Occupational Safety and Health (NIOSH). Physical health, specifically hearing ability, was assessed using a validated smartphone-based pure-tone audiometry application to measure hearing thresholds across multiple frequencies. The resulting data were used to calculate the pure-tone average (PTA) and classify hearing impairment according to the World Health Organization (WHO) standards. Psychological health was evaluated through a structured 14-item questionnaire developed for this study, covering self-reported impacts on stress, anxiety, sleep quality, concentration, communication, and emotional state. The results indicated a hazardous work environment, with the mean noise level across stations (86.67 dBA) significantly exceeding the NIOSH safety threshold. A high prevalence of hearing impairment was observed among operators, with 88% exhibiting impairment in the worse ear. A multiple linear regression analysis revealed that noise level, age, and duration of exposure were all statistically significant predictors, collectively explaining 62.3% of the variance in hearing impairment (F(3, 46) = 25.32, p < 0.001). The analysis further identified age as a key effect modifier; the duration of exposure was the dominant risk factor for younger workers, while the intensity of the noise level was more critical for older workers. Psychologically, workers reported a high prevalence of adverse effects, with sleep disturbances being the most common issue (reported by 75%), followed by emotional distress (67%) and anxiety (60%). This study also found a complete lack of hearing protection use and no formal training on noise hazards, highlighting significant gaps in occupational safety practices. Full article