Search Results (3,831)

This study explores the multifaceted attitudes of high school students toward the use of artificial intelligence (AI) and large language models (LLMs) like ChatGPT in educational contexts. Drawing upon a tripartite model of attitudes, our research evaluates affective, cognitive, and behavioral dimensions to offer a nuanced understanding of students’ perceptions. The affective dimension assesses emotional responses to AI tools, the cognitive dimension examines beliefs about the utility and ethical considerations of AI, and the behavioral dimension evaluates actual usage patterns of AI technologies. Utilizing a newly developed survey instrument tailored for the educational context, data was collected from 93 high school students across different regions of Italy in the period that ranged from February 2024–March 2024. Exploratory factor analysis (EFA) was employed to explore the underlying structure of the survey instrument and identify underlying factors influencing AI acceptance. The analysis reveals three distinct factors—Mindful AI Learning, Embracing AI Effects, and LLM as Learning Companion, highlighting the complexity of students’ attitudes toward AI. Results indicate a cautious but optimistic reception of AI in education, offering crucial insights into Information Intelligence for enhanced learning and the design of personalized learning pathways. The study contributes to the literature by offering a novel scale to measure attitudes toward artificial intelligence, specifically focusing on both general AI and Generative AI large language models, such as ChatGPT. Moreover, it highlights the critical need for AI literacy, ethical digital learning frameworks, and robust institutional policies to bridge the digital divide. Consequently, this work is framed as a preliminary exploratory investigation. Ultimately, these findings advance our knowledge of transformative digital learning processes and inform future strategies for human–machine integration in educational systems. Full article

The growing worldwide prevalence of Diabetes Mellitus highlights the urgent need for effective early detection methods to enable prompt intervention. This study develops a machine learning-based decision-support prototype for predicting diabetes risk using health metrics from the DiaHealth dataset, a recently published Bangladeshi open-source dataset for Type 2 diabetes prediction. Five supervised learning algorithms were evaluated: Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Decision Tree (DT), and Random Forest (RF). Models were assessed across three stages: before feature scaling, after standardisation, and following hyperparameter optimisation via GridSearchCV, using accuracy, precision, recall, and F1-score as evaluation metrics. LR and SVM showed marked improvements after standardisation, consistent with their sensitivity to feature magnitude, whilst tree-based approaches such as DT and RF remained largely unchanged. KNN displayed minimal sensitivity to scaling, which is discussed in relation to the feature distributions of the dataset. Following hyperparameter tuning, RF achieved the highest accuracy of 95%, outperforming all other models. RF predictions were interpreted using Local Interpretable Model-agnostic Explanations (LIME) to promote transparency in model decision-making. The best-performing model was subsequently deployed as an interactive web-based prototype application using Streamlit, providing real-time prediction outputs. These findings demonstrate how preprocessing choices and hyperparameter tuning can differentially affect algorithm performance and illustrate the potential of combining explainable AI with practical deployment for diabetes risk assessment in a research context. Full article

Background/Objectives: Iron deficiency remains a prevalent condition, needing specific laboratory tests for diagnosis. This study aimed to evaluate whether routine complete blood cell count (CBC) parameters can be used within a machine learning framework to predict low ferritin and low transferrin saturation, used as biochemical markers of altered iron status, potentially supporting more targeted laboratory test utilization. Methods: In this single-center retrospective outpatient study, we analyzed 32,437 records from subjects undergoing both complete blood cell count and iron metabolism testing between 2023 and 2026. Low ferritin and low transferrin saturation were defined using sex-specific thresholds. Low ferritin was present in 14,344 subjects (44.2%), whereas low transferrin saturation was present in 7791 subjects (24.0%). After cleaning data and excluding incomplete records, demographic variables and CBC indices were tested as potential predictors. The dataset was split into training and test sets with stratified sampling. Multiple supervised machine learning models, including logistic regression, decision tree, random forest, XGBoost, support vector machine, k-nearest neighbors, and Naive Bayes, were trained. Hyperparameter tuning and model selection were performed using repeated stratified 10-fold cross-validation, optimizing the area under the curve (AUC). Model performance was assessed by AUC, sensitivity, and specificity, and validated on an independent test set. Results: All models showed predictive capability for low ferritin and low transferrin saturation using CBC parameters alone. Ensemble methods, especially random forest and XGBoost, reached the best performance (AUC values of 0.80–0.87 for ferritin and 0.85–0.96 for transferrin saturation). Sensitivity and specificity were balanced, supporting clinical screening applicability. Results were maintained across validation and confirmed in the test set. Prediction of transferrin saturation showed slightly higher accuracy than ferritin. Feature importance analysis identified mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), and red blood cell distribution width (RDW) as key predictors. Conclusions: CBC-based machine learning models may help identify subjects with low ferritin or low transferrin saturation, supporting subsequent targeted assessment of iron status. Full article

Accurate and scalable urban land cover mapping is critical for sustainable urban planning and environmental management. While deep learning models offer powerful tools for this task, their performance is often constrained by the need for vast, manually labeled datasets, which are costly and challenging to acquire for diverse urban environments. To address this limitation, we propose the Cross-Scale U-Net, an original, highly adaptable operational framework that systematically exploits the inherent scale effects of remote-sensing imagery to optimize transfer learning. By operationalizing prior theoretical findings on receptive fields, this workflow provides an actionable method for users to manipulate spatial resolution, identify an optimal scale to bridge the domain gap, and subsequently automate feature extraction with significantly reduced manual effort. Using the well-annotated ISPRS Potsdam dataset as the source domain, our framework transfers learned knowledge to classify National Agriculture Imagery Program (NAIP) data from Phoenix, AZ (2015), into four primary land cover classes. We systematically evaluated the framework’s performance across spatial resolutions ranging from 15 cm to 100 cm, achieving a peak overall accuracy (OA) of 82.45%. To assess generalizability, the model was applied in a label-free transfer scenario to NAIP imagery from Las Vegas, NV (2015), and Phoenix, AZ (2013 and 2019), consistently delivering OA values above 70%. In a comparative analysis, the Cross-Scale U-Net significantly outperformed traditional classification techniques. While our current empirical validation is focused on arid urban environments due to experimental constraints, the framework introduces a highly flexible, actionable scale-adjustment process. This approach offers a scalable workflow that can be tailored to various landscape scales—such as expanding to coarser resolutions for large-scale forests or protected areas—delivering high-fidelity maps while mitigating data scarcity. Full article

Recurring load-shedding and persistent power system disruptions in South Africa have intensified the need for reliable data-driven assessment of electricity supply dynamics. Addressing this challenge requires comprehensive and well-structured datasets that capture the key operational characteristics of the electricity system. This paper presents a dataset on load-shedding and power system operations in South Africa, developed to support time series modelling and electricity reliability studies. The dataset comprises hourly observations obtained from the Electricity Supply Commission (Eskom) data portal covering the period from July 2018 to June 2023. It contains key electricity system variables, including load-shedding frequency, contracted demand, dispatchable generation, thermal generation, renewable energy generation, electricity imports, and planned and unplanned capability loss factors. The response variable, load-shedding, was pre-processed (discretised) to construct structured data suitable for count time series and machine learning to analyse temporal patterns, seasonality, and electricity supply disruptions. In addition, selected variables were combined to provide comprehensive measures of planned and unplanned capability reductions within the electricity system. The dataset provides a valuable resource for load-shedding analysis, reliability assessment, forecasting, energy planning, and policy development in South Africa. Full article

Accurate three-dimensional characterization of turbulent flows in natural waterways is essential for the effective design of tidal farms and other critical infrastructure situated along or across rivers. High-fidelity predictions based on the large-eddy simulation (LES) method capture the necessary physics but incur computational costs that hinder rapid scenario testing. Statistically, a relatively long history of instantaneous flow fields is required to generate reliable turbulence statistics, e.g., mean velocity and Reynolds stresses, of river flow. Such a requirement often incurs high simulation runtime and data storage costs. This study seeks to develop a neural network surrogate model that learns from a limited number of instantaneous flow realizations and approximates the outputs of the corresponding time-averaged fields with LES-level accuracy. Such a surrogate would eliminate the need to accumulate extensive ensembles, enabling faster hydrodynamic assessment and making LES-informed analyses more accessible for practical engineering decisions. Full article

The rising global population has heightened food demand, placing pressure on agricultural systems, particularly in water-scarce regions such as South Africa. Smallholder farmers, essential to the sector, face climatic variability and resource constraints, necessitating innovative solutions to enhance sustainability and productivity. This study evaluates unmanned aerial vehicles (UAVs) for generating spatially explicit evapotranspiration (ET) estimates in a small-scale sugarcane field, supporting precision water management. Vegetation indices (VIs) derived from UAV-based multispectral imagery were used to predict actual ET (ET_a) and validated against eddy covariance measurements. Five models were assessed, including Normalised Difference Vegetation Index (NDVI)-based and Enhanced Vegetation Index (EVI)-based approaches. Machine learning was used to relate crop coefficients (K_c) to NDVI, enabling improved estimation. The two-band EVI (EVI2) model achieved the highest accuracy, with an R² of 0.63, an RMSE of 0.67, and an MAE of 0.52. ET-VI approaches, particularly EVI2, require lower data and technical complexity, making them suitable for smallholder systems. However, reducing dependence on in situ data remains essential to improve accessibility of remote sensing approaches for agricultural water management in resource-limited environments. These findings demonstrate the potential of UAV-based ET_a modelling to support field-scale irrigation decision-making while highlighting the need for further refinement to improve operational applicability across diverse smallholder farming contexts and beyond. Full article

Purpose: To evaluate the effectiveness of serious games, including virtual reality-based interventions, in improving clinical skills acquisition among undergraduate and postgraduate health science students. Methods: This systematic review was prospectively registered in PROSPERO (CRD42024589035) and conducted in accordance with PRISMA 2020 guidelines. PubMed, Scopus, Web of Science, and ScienceDirect were searched from inception to 31 August 2025. Eligible studies examined serious games, simulation-based platforms, or immersive and non-immersive virtual reality interventions designed to support clinical skills development. Outcomes were classified using a predefined hierarchical framework aligned with Miller’s pyramid, distinguishing performance-based clinical competence, clinical reasoning, and secondary educational outcomes. Owing to substantial heterogeneity in interventions, comparators, and assessment methods, a narrative synthesis was performed. Results: Thirteen studies involving 892 participants were included. Serious games and virtual reality-based interventions were associated with generally favorable outcomes for knowledge acquisition, self-efficacy, motivation, satisfaction, and anxiety reduction. Improvements in clinical reasoning were reported in several studies, and some studies demonstrated benefits in performance-based clinical competence, particularly in simulation and virtual reality settings. However, findings for objective performance-based outcomes were mixed, with some studies reporting no statistically significant between-group differences. Heterogeneity in outcome definitions and limited reporting of standardized effect sizes reduced cross-study comparability. Conclusions: Serious games, including virtual reality-based interventions, may serve as complementary, scenario-based learning strategies in health sciences education. The most consistent effects were observed for cognitive and learner-centered outcomes, whereas evidence for objective gains in performance-based clinical competence remains variable. Further high-quality studies using standardized outcome frameworks, validated performance-based assessments, effect sizes, confidence intervals, and longer follow-up are needed. Full article

Dengue virus infection remains a significant public health challenge in endemic regions, with growing evidence of autochthonous transmission in Europe. Assessing serological exposure in high-risk populations such as military personnel deployed to endemic areas is essential to quantify exposure risk and support operational decision-making, particularly regarding pre-deployment counselling and risks associated with secondary infection. We conducted a cross-sectional study involving 1355 members of the Italian Armed Forces, measuring anti-dengue IgG antibodies by ELISA and collecting data on deployment history and exposure risk. Overall, IgG seropositivity was 8.12%, with significantly higher prevalence among individuals reporting travel or deployment to endemic regions (24.71%) compared with non-exposed personnel (4.27%). Seropositivity increased with age and correlated with a CDC-derived cumulative dengue risk score (Spearman’s ρ = 0.299, p < 0.0001). A multivariable logistic regression model including age and exposure risk achieved an AUC of 0.75, while machine-learning models provided complementary predictive assessment, with random forest reaching an AUC of 0.79. These findings indicate substantial anti-dengue IgG seropositivity compatible with previous dengue exposure among Italian military personnel, particularly those deployed to endemic settings. The study highlights the need for targeted surveillance and risk-based preventive strategies, and supports the use of exposure-based models to improve epidemiological assessment and inform vaccination strategies in mobile populations. Full article

This study examines the psychometric functioning of the Basic Learning Ability Assessment (BLAA), a high-stakes placement assessment used in Taiwan’s Adaptive Guidance Placement System (AGPS) for junior high school students with intellectual disabilities (IDs). The sample comprised 203 ninth-grade students with ID from 47 public junior high schools in Taiwan, all of whom completed three operational multiple-choice forms of the BLAA. Using classical test theory (CTT), we examined item difficulty using proportion-correct indices, item discrimination using upper–lower group discrimination indices, distractor functioning by comparing response patterns between higher- and lower-performing examinees, and internal consistency reliability using the Kuder–Richardson Formula 20 (KR-20). The results show that most items fell within the average-to-easy range and demonstrated acceptable to strong discrimination. Distractor functioning was generally satisfactory, with most items containing no nonfunctioning distractors. KR-20 coefficients ranged from 0.904 to 0.926, indicating high internal consistency within each form. Functional Language and Social Adaptation showed relatively stable psychometric patterns, whereas Mathematical Skills displayed greater variability in item difficulty, discrimination, and distractor functioning. Overall, the findings provide initial CTT-based internal psychometric evidence regarding the item functioning and form-level reliability of the BLAA, while highlighting the need for ongoing item refinement, particularly in the Mathematical Skills domain. Full article

Respiratory infectious diseases remain a major public health challenge due to the persistence of inadequate preventive behaviors and limited awareness of invisible contagion mechanisms. Although augmented reality (AR) has been increasingly adopted in educational applications, there is still a need for structured and user-centered approaches that integrate immersive interaction, pedagogical objectives, and usability-oriented development for preventive health education. This study presents the design and development of an AR serious game, “Covidcito Malhechor”, aimed at supporting preventive health education through immersive learning experiences. The proposed contribution combines the iPlus methodology with the Scrum agile framework to provide a structured and replicable process for developing AR-based serious games. The system enables users to visualize virtual representations of viruses and contamination processes within real-world environments while interacting with gamified preventive health scenarios. The solution integrates pedagogical objectives, gamification elements, and AR-based interaction mechanics within a human-centered design approach focused on usability and accessibility. The system was evaluated through performance testing, functional validation, and usability assessment involving 40 students. Results demonstrated stable execution on ARCore-compatible mobile devices, achieving a successful completion of all functional test cases after iterative refinement. The usability evaluation using the Serious Games Usability Evaluation Instrument (SGUEI) yielded an overall score of 83.14%, indicating a high level of perceived usability and interaction quality. These findings demonstrate the technical feasibility and usability of the proposed approach and support its potential as a foundation for future studies on AR-based preventive health education. Full article

In the current higher education landscape, students frequently resort to “cramming” or massed study practices, which often lead to superficial learning and rapid information decay rather than long-term memory (LTM) consolidation. This systematic review aims to analyze the evidence on the effectiveness of neurodidactic strategies based on spaced learning for LTM consolidation in university contexts. Following the PRISMA statement and the PICOS model, a comprehensive search was conducted in Scopus and Web of Science, identifying 19 empirical studies that met the eligibility criteria. The corpus was then subjected to a risk of bias assessment using RoB-2, ROBINS-I, and MMAT. The results indicate that neurodidactic strategies—categorized into operative, methodological, and socio-emotional types—are associated with improved knowledge retention in several contexts when learning episodes are distributed over time. Some studies report positive trends in retention compared to massed practice, particularly in health sciences and language learning, but the heterogeneity of methodologies and outcome measures limits definitive conclusions. Therefore, while the integration of spaced learning within a neurodidactic framework appears promising, the evidence should be interpreted as suggestive rather than conclusive, and further research is needed to confirm these observations across diverse settings. This systematic review has been registered in the Open Science Framework (OSF). Full article

Accurate fault classification of electro-hydrostatic actuators (EHAs) remains challenging because multivariate fault signals contain local transient variations, inter-variable coupling, and dynamic temporal dependencies that are difficult to capture simultaneously using a single model. To address this problem, this paper proposes a multi-view temporal feature collaborative heterogeneous ensemble learning model (MTF-HEM) for EHA multivariate time series fault classification. MTF-HEM integrates a representative subsequence-guided time series forest (RSG-TSF), XGBoost, and a lightweight LSTM to extract local morphological, global statistical, and temporal dependency features, respectively. The outputs of these heterogeneous base learners are fused using a bootstrap-driven out-of-bag probability binning stacking (BOPB-stacking) strategy. The proposed method was evaluated on an AMESim-based simulated EHA plunger pump fault dataset containing one normal condition and six fault conditions. Under the present simulation setting, MTF-HEM achieved an accuracy of 99.52% and outperformed the tested deep time series classification models, ensemble models, and individual base learners. These results suggest that multi-view heterogeneous feature fusion can improve the classification of simulated EHA fault time series and provide a methodological reference for intelligent actuator fault diagnosis. However, the current validation is based on data generated from a single AMESim simulation model, and further evaluation on real EHA systems is needed to assess the practical applicability and generalizability of the proposed approach. Full article

Background: Type II workplace violence by patients, relatives, or visitors is an occupational health and patient-safety concern in primary care. Cranston Ridge Medical Clinic (CRMC), a single urban family medicine and walk-in primary care clinic in Calgary, Alberta, plans to implement a universal, risk-informed workplace-safety bundle that is based on observable behaviour, situational risk, and documented safety concerns rather than demographic profiling. Methods: This article describes a single-site internal quality improvement and workplace-safety evaluation protocol. The comparison is CRMC usual practice during the pre-implementation baseline period; there is no concurrent external control group. The planned evaluation will use aggregate, de-identified operational data from a 12-month pre-implementation baseline, a four-week implementation period, and 12 months of post-implementation monitoring. All clinic staff will receive workplace-safety training as part of routine implementation. No staff, patients, or visitors will be recruited as research participants, and the evaluation will not use individual-level staff survey, interview, or focus-group data. Patient/visitor information will be used only as aggregate operational monitoring data when needed to assess safety, access, patient flow, and complaints. Intervention and analysis: The bundle includes worksite analysis, staff training, a brief arrival safety screen, a response algorithm, standardized reporting, monthly safety huddles, and post-incident support. The primary metric will be the Type II workplace-violence incident rate per 1000 clinic visits. Planned analyses include run charts, pre–post rate ratios, and Poisson or negative binomial segmented regression if monthly counts are sufficient. Implementation learning will be summarized from routine training records, safety-huddle summaries, post-incident debrief themes, and other aggregate de-identified operational indicators. Expected contribution: The protocol contributes a transparent, equity-sensitive, and operationally feasible model for balancing staff safety with patient access in primary care. Full article

Background/Objectives: Acute care use (ACU)—emergency department visits, inpatient hospitalizations, and observation stays—drives morbidity and costs among adults with diabetes. We developed and evaluated machine-learning models to predict 1-year ACU risk using electronic health record (EHR) data and neighborhood-level data. Methods: We performed a retrospective cohort study using de-identified EHR data from a large urban academic health center, including adults (≥18 years) with diabetes (N = 23,052). The index date was defined as one year before each patient’s last encounter, and ACU was assessed during the subsequent year. We modeled 180 predictors spanning demographics, Area Deprivation Index (ADI), prior healthcare utilization, vitals/BMI, comorbidities, medications, and laboratory results. Decision tree and gradient-boosted models (XGBoost, LightGBM, CatBoost) were tuned with Optuna using 8-fold stratified cross-validation, optimizing area under the receiver operating characteristic curve (AUC). To improve class-balanced classification performance under outcome imbalance, we selected post hoc probability thresholds that maximized Macro F1 and quantified interpretability with permutation feature importance. Results: ACU occurred in 30.53% of patients (7039/23,052). Boosted models achieved AUC ≈ 0.78, with LightGBM performing best (AUC = 0.7839). Macro F1–optimized thresholds (<0.5; typically 0.375–0.40) improved class-balanced performance versus a 0.5 cutoff. Across boosted models, prior utilization features dominated, followed by discharge-related factors and neighborhood deprivation; comorbidities and laboratory results contributed. Conclusions: In this single urban academic health-system cohort of adults with diabetes, EHRbased boosted models demonstrated moderate discrimination for predicting 1-year ACU and identified interpretable predictive signals. Threshold optimization improved class-balanced statistical performance. Prior utilization, care transitions, and neighborhood deprivation emerged as dominant predictive features. External and temporal validation are needed before broader application. Full article