Search Results (376)

Background: Gamification is an innovative pedagogical strategy for improving learning outcomes, motivation, engagement, and knowledge retention. Nevertheless, evidence on the effectiveness of gamification remains heterogeneous. Methods: A systematic review was conducted. Searches were performed across PubMed/MEDLINE, CINAHL, PsycINFO, Scopus, Web of Science, Google Scholar, and grey literature (2015–2025). Eligible studies included quantitative, qualitative, and mixed-methods research involving undergraduate nursing students exposed to gamification interventions. Data extraction and quality assessment were independently performed using RoB-2, ROBINS-I, and JBI tools. Narrative synthesis was adopted due to the heterogeneity of interventions and outcome measures. Results: A total of 48 studies were included. Gamification strategies varied widely and included interactive quizzes, gamified flipped classroom models, serious games with explicit game elements, escape rooms, digital badges, and audience-response systems. For learning outcomes, most studies reported improvements in knowledge or performance, particularly when gamification included immediate feedback and repeated practice. While the knowledge retention was evaluated less frequently (12%), it was generally maintained or improved up to 2–4 weeks and across semester assessments. Strong positive trends of motivation and engagement were found across most studies, especially with competitive quizzes, missions, and narrative-based activities. Self-efficacy and satisfaction frequently improved, particularly in gamified simulations and team-based activities. Risk of bias was variable, with many quasi-experimental and descriptive studies limiting causal inference. Evidence certainty ranged from low to moderate according to GRADE criteria. Conclusions: Gamification is a promising educational approach in undergraduate nursing programs. Effects on long-term retention and practical skills remain less clear due to methodological variability and limited follow-up data. Future research focused on standardized outcome measures and longer follow-up intervals is required to consolidate evidence and guide educational policy. Protocol registered on PROSPERO (CRD420251117719). Full article

Machine learning (ML) has become a cornerstone of critical applications, but its vulnerability to data poisoning attacks threatens system reliability and trustworthiness. Prior studies have begun to investigate the impact of data poisoning and proposed various defense or evaluation methods; however, most efforts remain limited to quantifying performance degradation, with little systematic comparison of internal behaviors across model architectures under attack and insufficient attention to interpretability for revealing model vulnerabilities. To tackle this issue, we build a reproducible evaluation pipeline and emphasize the importance of integrating robustness with interpretability in the design of secure and trustworthy ML systems. To be specific, we propose a unified poisoning evaluation framework that systematically compares traditional ML models, deep neural networks, and large language models under three representative attack strategies including label flipping, random corruption, and adversarial insertion, at escalating severity levels of 30%, 50%, and 75%, and integrate LIME-based explanations to trace the evolution of model reasoning. Experimental results demonstrate that traditional models collapse rapidly under label noise, whereas Bayesian LSTM hybrids and large language models maintain stronger resilience. Further interpretability analysis uncovers attribution failure patterns, such as over-reliance on neutral tokens or misinterpretation of adversarial cues, providing insights beyond accuracy metrics. Full article

The integration of artificial intelligence into remote patient monitoring (RPM) offers significant benefits for proactive and continuous healthcare, but also raises critical concerns regarding privacy, integrity, and robustness. Federated Learning (FL) provides a decentralized approach to model training that preserves data locality, yet most existing solutions address only isolated security aspects and lack contextual adaptability for clinical use. This paper presents MedGuard-FL, a context-aware FL framework tailored to e-healthcare environments. Spanning device, edge, and cloud layers, it integrates encryption, adaptive differential privacy, anomaly detection, and Byzantine-resilient aggregation. At its core, a policy engine dynamically adjusts privacy and robustness parameters based on the patient’s status and the system’s risk. Evaluations on real-world clinical datasets show MedGuard-FL maintains high model accuracy while neutralizing various adversarial attacks (e.g., label-flip, poisoning, backdoor, membership inference), all with manageable latency. Compared to static defenses, it offers improved trade-offs between privacy, utility, and responsiveness. Additional edge-level privacy analyses confirm its resilience, with attack effectiveness near random. By embedding clinical risk awareness into adaptive defense mechanisms, MedGuard-FL lays a foundation for secure, real-time federated intelligence in RPM. Full article

The study aims to establish a comprehensive framework aligning institutional governance, pedagogical theories, and teaching practice for the sustainable adoption of AI-facilitated digital representatives of human instructors in higher education videos within universities. The study employs a systemic qualitative approach and grounded theory principles to analyze administrative/legal documents and academic publications. The methodology includes source searching and screening, automated text analysis using the Lexalytics tool, clustering and thematic interpretation of the findings, and a subsequent discussion of the emerging perspectives. Following the analysis of international/supranational/national regulations, the findings reveal a significant regulatory gap for humans’ digital representatives in educational videos and suggest a governance baseline for tailored institutional guidelines that address data protection, copyright, and ethical compliance. Theoretically, the study synthesizes evidence-informed educational theories and concepts to form a robust theoretical foundation for using humans’ digital representatives in higher education instructional videos and identifies constructivism, student-centered personalized learning, multimodal multimedia-based learning principles, smart and flipped classrooms, and post-digital relations pedagogy as crucial foundational concepts. The findings suggest a thematic taxonomy that outlines diverse digital representative types, their varying efficiency based on knowledge and course type, and university community attitudes highlighting benefits and challenges. The overall contribution of this research lies in an integrated interdisciplinary framework—including the legal context, pedagogical theory, and promising practices—that guides the responsible use of digital human representatives in higher education videos. Full article

In urban underground space construction using shield tunnelling, the geological conditions ahead of the tunnel face are often uncertain. Without timely and accurate classification of the ground type, mismatches in operational parameters, uncontrolled costs, and schedule risks are likely to occur. Using observations from an earth pressure balance (EPB) project on an urban railway, a data-driven classification framework is developed that integrates shield tunnelling operating measurements with physically derived quantities to discriminate among soft soil, hard rock, and mixed strata. Principal component analysis (PCA) is performed on the training set, followed by a systematic comparison of tree-based classifiers and hyperparameter optimization strategies to explore the attainable performance. Under unified evaluation criteria, a categorical bosting (CatBoost) model optimized by a Nevergrad combination strategy (NGOpt) attains the highest test accuracy of 0.9625, with macro-averaged precision and macro-averaged recall of 0.9715 and 0.9716, respectively. To mitigate optimism from single-point estimates, stratified bootstrap intervals are reported for the test set. A Monte Carlo experiment applies independent perturbations to the PCA-transformed features, producing low label-flip rates across the three classes, with only minor changes in probability calibration metrics, which suggests consistent decisions under sensor noise and sampling bias. Overall, within the scope of the considered EPB project, the study delivers a compact workflow that demonstrates the feasibility of uncertainty-aware ground-type classification and provides a methodological reference for developing decision-support tools in underground tunnel construction. Full article

Background: Interstitial myocardial fibrosis is a crucial pathological feature of many cardiovascular disorders. Myocardial fibrosis resulting in extracellular volume (ECV) expansion can be quantified via cardiac MRI (CMR) with T₁ mapping before and after minimally invasive gadolinium (Gd) contrast agent administration. However, longitudinal repetitive ECV measurements are challenging in rodents due to the prolonged scan time with cardiac and respiratory gating that is required for conventional T₁ mapping and the invasive nature of the rodent intravenous lines. Methods: To address these challenges, the objective of this study is to establish a fast, free-breathing, and gating-free ECV procedure using a minimally invasive subcutaneous catheter for in-scanner Gd administration that can allow longitudinal repetitive ECV evaluations in rodent models. This is achieved by the (1) IntraGate sequence for free-breathing, gating-free cardiac imaging; (2) minimally invasive subcutaneous in-scanner Gd administration; and (3) fast T₁ mapping with a varied flip angle (VFA) in conjunction with (4) triple jugular vein blood T₁ normalization. Additionally, full cine CMR (multi-slice short-axis, long-axis 2-chamber, and long-axis 4-chamber) was acquired during the waiting period to assess comprehensive cardiac function and strain. Results: We successfully established a minimally invasive fast ECV quantification protocol to enable longitudinal repetitive ECV quantifications in rodents. Minimally invasive subcutaneous Gd bolus administration induced a reasonable dynamic contrast enhancement (DCE) time course, reaching a steady state in ~20 min for stable T₁ quantification. The free-breathing gating-free VFA T₁ quantification scheme allows for rapid cardiac (~2.5 min) and jugular vein (49 s) T₁ quantification with no motion artifacts. The triple jugular vein T₁ acquisitions (1 pre-contrast and 2 post-contrast) immediately flanking the heart T₁ acquisitions enable accurate myocardial ECV quantification. Our data demonstrated that left-ventricular myocardial ECV quantification was highly reproducible with repeated scans, and the ECV values (0.25) are comparable to reported ranges among humans and rodents. This protocol was successfully applied to the ischemia–reperfusion injury model to detect myocardial fibrosis, which was validated by histopathology. Conclusions: We established a simple, fast, minimally invasive, and robust CMR protocol in rodents that can enable longitudinal repetitive ECV quantification for cardiovascular disease progression. It can be used to monitor disease regression with interventions. Full article

Chickpeas are a pulse crop that originated in Eurasia and are a source of protein for many people. The objective of this research is to select stable, high-yielding chickpea genotypes using uni- and multivariate methods of adaptability and stability analysis. Fifteen genotypes were tested in the 2020 and 2021 agricultural years. The experimental design was a completely randomized block design with three replications. The collected data were yield (kg/ha) values, and the stability analyses were performed using Eberhart and Russell’s, Lin and Binns’s modified by Carneiro’s, additive main effects and multiplicative interaction (AMMI), and weighted average of absolute scores (WAASB) methods. The average sum of ranks (ASR) was then calculated by ranking genotypes according to their yield and stability indices. The AMMI analysis of variance showed significant effects (p < 0.05) for environments, genotypes, and the interaction between genotypes and environments. From AMMI, the first three principal components (PCs) had significant effects, and the cumulative variance on the PC1 and PC2 axes was 86%. FLIP02-23C, FLIP03-109C, and Jamu 96 had the lowest ASR, indicating that these genotypes are the most stable and productive chickpea genotypes. According to AMMI2, genotypes FLIP03-109C, FLIP03-35C, FLIP02-23C, and FLIP06-155C could be adapted to irrigated environments. Full article

Background: The early and accurate classification of ischemic stroke stages on computed tomography (CT) remains challenging due to subtle attenuation differences and significant scanner variability. This study developed a neural network framework to dynamically optimize Hounsfield Unit (HU) transformations and CLAHE parameters for temporal stage-specific stroke classification. Methods: We analyzed 1480 CT cases from 68 patients across five stages (hyperacute, acute, subacute, chronic, and normal). The training data were augmented via horizontal flipping, ±7° rotation. A convolutional neural network (CNN) was used to optimize linear transformation and CLAHE parameters through a combined loss function incorporating the effective measure of enhancement (EME), peak signal-to-noise ratio (PSNR), and regularization. the enhanced images were classified using logistic regression (LR), support vector machines (SVMs), and random forests (RFs) with 25-fold cross-validation. Model interpretability was evaluated using Grad-CAM. Results: Neural network optimization significantly outperformed static parameters across validation metrics. Deep CLAHE achieved the following accuracies versus static CLAHE: hyperacute (0.9838 vs. 0.9754), acute (0.9904 vs. 0.9873), subacute (0.9948 vs. 0.9825), and chronic (near-perfect 0.9979 vs. 0.9808). Qualitative interpretability analysis confirmed that models focused on clinically relevant regions, with optimized enhancement producing more coherent attention patterns than static methods. Parameter analysis revealed stage-aware adaptation: conservative enhancement in early phases (slope: 1.249–1.257), maximized in subacute (slope: 1.290–1.292), and restrained in the chronic phase (slope: 1.240–1.258), reflecting underlying stroke pathophysiology. Conclusions: A neural network-optimized framework with interpretability validation provides stage-specific stroke classification that achieves superior performance over static methods. Its pathophysiology-aligned parameter adaptation offers a clinically viable and transparent solution for emergency stroke assessment. Full article

Programmable data planes are increasingly essential for enabling In-band Network Telemetry (INT), fine-grained monitoring, and congestion-aware packet processing. Although the P4 language provides a high-level abstraction to describe such behaviors, implementing them efficiently on FPGA-based platforms remains challenging due to hardware constraints and limited compiler support. Building on P4THLS framework, which leverages HLS for FPGA data-plane programmability, this paper extends the approach by introducing support for P4-style stateful objects and a structured metadata propagation mechanism throughout the processing pipeline. These extensions enrich pipeline logic with real-time context and flow-level state, thereby facilitating advanced applications while preserving programmability. The generated codebase remains extensible and customizable, allowing developers to adapt the design to various scenarios. We implement two representative use cases to demonstrate the effectiveness of the approach: an INT-enabled forwarding engine that embeds hop-by-hop telemetry into packets and a congestion-aware switch that dynamically adapts to queue conditions. Evaluation of an AMD Alveo U280 FPGA implementation reveals that incorporating INT support adds roughly 900 LUTs and 1000 Flip-Flops relative to the baseline switch. Furthermore, the proposed meter maintains rate measurement errors below 3% at 700 Mbps and achieves up to a 5× reduction in LUT and 2× reduction in Flip-Flop usage compared to existing FPGA-based stateful designs, substantially expanding the applicability of P4THLS for complex and performance-critical network functions. Full article

This study examines university teachers’ digital competences during Emergency Remote Teaching at three Spanish institutions—the University of La Laguna, the University of Extremadura, and the University of Valladolid—and, from the faculty perspective, appraises hybrid teaching experiences and institutional support services. We employed a qualitative multi-case design using semi-structured focus-group interviews and discussion groups with 57 instructors from Social Sciences and Humanities, Engineering, and Health Sciences, selected via purposive sampling. Data were deductively coded in Atlas.ti 24. Faculty perceive hybrid teaching as useful for widening access and repositioning the virtual campus as a communicative hub; they highlight Moodle, videoconferencing, content-authoring tools such as H5P, and methodologies like gamification and flipped learning to enhance motivation. Nonetheless, generational gaps and concerns about the authenticity of online assessment persist, supporting continued reliance on in-person examinations. Technical and training support services are viewed positively, yet respondents call for more staffing and stronger dissemination of teaching resources. Consolidating teachers’ digital competences requires institutional policies that integrate robust infrastructure, contextualized continuous professional development, and communities of practice to ensure the sustainability of hybrid models in higher education at the national level. Full article

The discovery of the fifth gravitational wave, GW170817, and its electromagnetic counterpart, resulting from the merger of neutron stars by the LIGO and Virgo teams, marked a major milestone in astronomy. It was the first time that gravitational waves and light from the same cosmic event were observed simultaneously. The LIGO detectors in the United States recorded the signal for 100 s, longer than in previous detections. The merging of neutron stars emits both gravitational and electromagnetic waves across all frequencies—from radio to gamma rays. However, pinpointing the exact source remains difficult, requiring rapid sky scanning to locate it. To address this challenge, the Gravitational-Wave Optical Transient Observer (GOTO) project was established. It is specifically designed to detect optical light from transient events associated with gravitational waves, enabling faster follow-up observations and a deeper study of these short-lived astronomical phenomena, which appear and disappear quickly in the universe. In astrophysics, it has become more important to find astronomical transient events like supernovae, gamma-ray bursts, and stellar flares because they are linked to extreme cosmic processes. However, finding these short-lived events in huge sky survey datasets, like those from the GOTO project, is very hard for traditional analysis methods. This study suggests a deep learning methodology employing Convolutional Neural Networks (CNNs) to enhance transient classification. CNNs are based on how biological vision systems work and how they are structured. They mimic how animal brains hierarchically process visual information, making it possible to automatically find complex spatial patterns in astronomical images. Transfer learning and fine-tuning on pretrained ImageNet models are utilized to emulate adaptive learning observed in biological organisms, enabling swift adaptation to new tasks with minimal data. Data augmentation methods like rotation, flipping, and noise injection mimic changes in the environment to improve model generalization. Dropout and different batch sizes are used to stop overfitting, which is similar to how biological systems use redundancy and noise tolerance. Ensemble learning strategies, such as Soft Voting and Weighted Voting, draw inspiration from collective intelligence in biological systems, integrating multiple CNN models to enhance decision-making robustness. Our findings indicate that this bio-inspired framework substantially improves the precision and dependability of transient detection, providing a scalable solution for real-time applications in extensive sky surveys such as GOTO. Full article

Vision–language models (VLMs) show strong potential for remote-sensing scene classification but still struggle with fine-grained categories and distribution shifts. We introduce a hierarchical prompting framework that decomposes recognition into a coarse-to-fine decision process with structured outputs, combined with parameter-efficient adaptation using LoRA/QLoRA. To evaluate robustness without depending on external benchmarks, we construct five protocol variants of the AID (V₀–V₄) that systematically vary label granularity, class consolidation, and augmentation settings. Each variant is designed to align with a specific prompting style and hierarchy. The data pipeline follows a strict split-before-augment strategy, in which augmentation is applied only to the training split to avoid train-test leakage. We further audit leakage using rotation/flip–invariant perceptual hashing across splits to ensure reproducibility. Experiments on all five AID variants show that hierarchical prompting consistently outperforms non-hierarchical prompts and matches or exceeds full fine-tuning, while requiring substantially less compute. Ablation studies on prompt design, adaptation strategy, and model capacity—together with confusion matrices and class-wise metrics—indicate improved recognition at both coarse and fine levels, as well as robustness to rotations and flips. The proposed framework provides a strong, reproducible baseline for remote-sensing scene classification under constrained compute and includes complete prompt templates and processing scripts to support replication. Full article

Background/Objectives: Artificial intelligence (AI) has been increasingly used to support radiological assessment in dentistry. We benchmarked machine learning (ML), deep learning (DL), and a hybrid optimization-assisted approach for the automatic five-class image-level classification of dental restorations (filling, implant, root canal treatment, fixed partial denture/bridge, crown) on panoramic radiographs. Methods: We analyzed 353 anonymized panoramic images comprising 2137 labeled restorations, acquired on the same device. Images were cropped and enhanced (histogram equalization and CLAHE), and texture features were extracted with GLCM. A three-stage pipeline was evaluated: (i) GLCM-based features classified by conventional ML and a baseline DL model; (ii) Hybrid Grey Wolf–Particle Swarm Optimization (HGWO-PSO) for feature selection followed by SVM; and (iii) a CNN trained end-to-end on raw images. Performance was assessed with an 80/20 per-patient split and 5-fold cross-validation on the training set. While each panoramic radiograph may contain multiple restorations, in this study we modeled the task as single-label, image-level classification (dominant restoration type) due to pipeline constraints; this choice is discussed as a limitation and motivates multi-label, localization-based approaches in future work. The CNN baseline was implemented in TensorFlow 2.12 (CUDA 11.8/cuDNN 8.9) and trained with Adam (learning rate 1 × 10⁻⁴), with a batch size 32 and up to 50 epochs with early stopping (patience 5); data augmentation included horizontal flips, ±10° rotations, and ±15% brightness variation. A post hoc power analysis (G*Power 3.1; α = 0.05, β = 0.2) confirmed sufficient sample size (n = 353, power > 0.84). Results: The HGWO-PSO + SVM configuration achieved the highest accuracy (73.15%), with macro-precision/recall/F1 = 0.728, outperforming the CNN (68.52% accuracy) and traditional ML models (SVM 67.89%; DT 59.09%; RF 58.33%; K-NN 53.70%). Conclusions: On this single-center dataset, the hybrid optimization-assisted classifier moderately improved detection performance over the baseline CNN and conventional ML. Given the dataset size and class imbalance, the proposed system should be interpreted as a decision-supportive tool to assist dentists rather than a stand-alone diagnostic system. Future work will target larger, multi-center datasets and stronger DL baselines to enhance generalizability and clinical utility. Full article

Aero-engine ablation detection is a critical task in aircraft health management, yet existing rotation-based object detection methods often face challenges of high computational complexity and insufficient local feature extraction. This paper proposes an improved YOLOv11 algorithm incorporating Context-guided Large-kernel attention and Rotated detection head, called CLR-YOLOv11. The model achieves synergistic improvement in both detection efficiency and accuracy through dual structural optimization, with its innovations primarily embodied in the following three tightly coupled strategies: (1) Targeted Data Preprocessing Pipeline Design: To address challenges such as limited sample size, low overall image brightness, and noise interference, we designed an ordered data augmentation and normalization pipeline. This pipeline is not a mere stacking of techniques but strategically enhances sample diversity through geometric transformations (random flipping, rotation), hybrid augmentations (Mixup, Mosaic), and pixel-value transformations (histogram equalization, Gaussian filtering). All processed images subsequently undergo Z-Score normalization. This order-aware pipeline design effectively improves the quality, diversity, and consistency of the input data. (2) Context-Guided Feature Fusion Mechanism: To overcome the limitations of traditional Convolutional Neural Networks in modeling long-range contextual dependencies between ablation areas and surrounding structures, we replaced the original C3k2 layer with the C3K2CG module. This module adaptively fuses local textural details with global semantic information through a context-guided mechanism, enabling the model to more accurately understand the gradual boundaries and spatial context of ablation regions. (3) Efficiency-Oriented Large-Kernel Attention Optimization: To expand the receptive field while strictly controlling the additional computational overhead introduced by rotated detection, we replaced the C2PSA module with the C2PSLA module. By employing large-kernel decomposition and a spatial selective focusing strategy, this module significantly reduces computational load while maintaining multi-scale feature perception capability, ensuring the model meets the demands of high real-time applications. Experiments on a self-built aero-engine ablation dataset demonstrate that the improved model achieves 78.5% mAP@0.5:0.95, representing a 4.2% improvement over the YOLOv11-obb which model without the specialized data augmentation. This study provides an effective solution for high-precision real-time aviation inspection tasks. Full article

As an important sustainable lifelong learning competence, self-regulated learning involves a continuous process of self-monitoring and self-directing towards a learning goal. This study examined the level of alignment between university students’ self-regulated learning (SRL) profiles using questionnaire data and learning analytics data in flipped classrooms. On the one hand, a hierarchical cluster analysis using the questionnaire data generated two learning profiles of high and low self-regulated (SR) learners. On the other hand, a hierarchical cluster analysis using the questionnaire data produced two learning profiles of active and passive online learners. Although a cross-tabulation analysis showed a significant and positive relationship between students’ learning profiles identified using the questionnaire and learning analytics data, the association was rather weak. Of the high SR learners, there was a significantly higher proportion of active online learners than passive online learners. In contrast, among low SR learners, a significantly lower proportion of active online learners than passive online learners was found. Furthermore, high SR and active online learners and high SR and passive online learners had significantly better academic achievement than low SR and active online learners and low SR and passive online learners, demonstrating the importance of SR in flipped classrooms. Full article