Search Results (38,819)

Class imbalance in clinical electrocardiogram (ECG) datasets limits the diagnostic sensitivity of automated arrhythmia classifiers, particularly for rare but clinically significant beat types. We propose a three-stage hybrid generative pipeline that combines a spectral-guided conditional variational autoencoder (cVAE), a class-conditional latent denoising diffusion probabilistic model (DDPM), and a Quantum Latent Refinement (QLR) module built on parameterized quantum circuits, implemented and evaluated using a classical quantum-circuit simulator, to augment minority arrhythmia classes, and present results based on the MIT-BIH Arrhythmia Database. The QLR module applies a bounded residual correction guided by Maximum Mean Discrepancy minimization to align synthetic latent distributions with real class-specific latent banks. A lightweight 1D MobileNetV2 classifier evaluated over ten independent random seeds and four augmentation ratios serves as the downstream benchmark. Our findings establish latent diffusion augmentation as an effective strategy for imbalanced ECG classification. To our knowledge, the proposed QLR module is the first use of a parameterized quantum circuit as a distributional refiner within a generative augmentation pipeline. While its performance is comparable to that of the classical latent diffusion framework under the present experimental conditions, the proposed approach demonstrates the feasibility of integrating quantum latent operators into generative medical AI pipelines and provides a foundation for future investigations on quantum-enhanced representation learning and data augmentation. Full article

Background: Robotic liver resections (RLRs) are rapidly expanding, yet the association between the learning curve, procedural complexity, and outcomes at intermediate-volume centers remains poorly defined. We evaluated the learning-curve trajectory and perioperative outcomes of a single surgeon’s initial RLR experience according to procedural complexity (IWATE difficulty score). Methods: We retrospectively analyzed 58 consecutive RLRs at an intermediate-volume center. We stratified outcomes by IWATE difficulty category and chronological tertile (early/middle/late). Textbook outcomes (TOs) and a composite failure endpoint (conversion, major complications [Clavien–Dindo ≥ IIIa] and 90-day mortality) were also assessed. Learning-curve behavior was examined with CUSUM and risk-adjusted CUSUM (RA-CUSUM) analyses. Results: Fifty-four procedures (93.1%) were minor resections and four were major hepatectomies; two were classified as IWATE Expert difficulty. Median estimated blood loss was 100 mL; conversion occurred in 10.3%, overall morbidity in 10.3% and severe complications (Clavien–Dindo ≥ IIIa) in 3.4%, with no mortalities within 90 days. TOs were achieved in 69.0% using the Delphi (TOLS) definition and in 46.6% using a length-of-stay-extended definition. Operative time and length of stay increased significantly with IWATE difficulty (p < 0.001 and p = 0.030), as did the composite failure endpoint (p = 0.039), whereas blood loss and complications did not. TOs decreased with difficulty under the extended definition (p = 0.016). No outcome except estimated blood loss differed across chronological tertiles (p = 0.032). Operative time was associated with the IWATE score (26.3 min per point; R² = 0.32) but not with case order (p = 0.93). CUSUM and RA-CUSUM curves showed a non-linear, multiphase pattern without an identifiable inflection point, with extremes attributable to individual high-complexity procedures. Conclusions: In this exploratory single-surgeon series, consisting predominantly of minor resections, no case-number threshold could be identified, and perioperative outcomes were more closely associated with procedural complexity than with chronological experience, supporting a complexity-adjusted interpretation of RLR outcomes rather than a fixed case-number learning threshold. Full article

The automatic inspection of airport infrastructure, specifically horizontal surface markings and Airfield Ground Lighting (AGL), is a critical task for maintaining aviation safety and operational efficiency. As the aviation industry shifts from manual surveys to automated visual inspections utilizing unmanned aerial vehicles (UAVs) and smart service vehicles, the demand for robust, real-time computer vision systems has surged. However, deploying computationally intensive deep learning models in the field introduces severe Size, Weight, and Power (SWaP) constraints. This paper presents a comprehensive framework for the semantic segmentation of runway/taxiway markings and the point-localization of AGL lamps, specifically focusing on the deployment paradigm shift from the expensive, GPU-accelerated heterogeneous system on chip (SoC) to highly efficient, dedicated Neural Processing Units (NPUs). We evaluate the performance of U-Net, LinkNet, U-Net-Point and HRNet-Lite-Point architectures trained on a custom dataset from the Poznań-Ławica Airport. Crucially, this study conducts a rigorous comparative hardware analysis between the flagship NVIDIA Jetson AGX Orin and a highly cost-effective heterogeneous setup comprising a Raspberry Pi 5 augmented with an NPU Hailo-8 AI accelerator. Experimental results demonstrate that while both platforms achieve real-time inference, the Hailo-8 integration fundamentally disrupts the traditional cost-to-performance ratio. Furthermore, the Hailo-8 configuration consumed less electrical power and memory footprint required by the Jetson, proving that dedicated NPUs are vastly superior for continuous, battery-operated edge deployment in autonomous airport maintenance systems. Specifically, the Raspberry Pi setup with the Hailo-8 accelerator demonstrated superior energy efficiency, requiring a significantly lower energy consumption per processed video frame compared to the Jetson platform. Full article

Science, Technology, Engineering, Arts, and Mathematics (STEAM) education has been increasingly recognized for its potential to promote early childhood development, while inclusion has become a fundamental principle of early childhood education. However, research and practice on STEAM in reverse inclusive activities remain limited. This study aimed to explore whether STEAM in reverse inclusive activities in preschools works and how it works. Participants included 6 children with special education needs and 22 typically developing children aged 4–6 years from a public preschool in China. The Assessment, Evaluation, and Programming System Chinese version was used to assess children’s early childhood development in daily routines and during STEAM in reverse inclusive activities. The findings indicated that STEAM in reverse inclusive activities in preschool was effective, with both typically developing children and children with special educational needs demonstrating developmental gains. Children’s early development within the activities was facilitated by the integration of art, embodied learning, effective peer interaction, and flexible teacher support responsive to children’s inquiry problems. Overall, this study provided initial evidence regarding the implementation and effectiveness of STEAM in reverse inclusive activities and offered practical implications for promoting early childhood development. Full article

The rapid growth of organisational textual data has increased the value of Natural Language Processing (NLP) and semantic analytics for strategic decision support. However, many employees still lack the knowledge and skills needed to evaluate AI-generated information critically. This study develops an explainable Management Information Systems (MIS) framework that integrates NLP-based semantic analytics with PLS-SEM to examine the relationship between AI illiteracy and strategic decision quality. A convergent mixed-methods design with sequential analytical integration was used with a valid sample of 200 knowledge workers from public organisations in Saudi Arabia across six industries. The sample included employees from Saudi Arabia, Egypt, Jordan, Sudan, Syria, India, and the Philippines. Quantitative data were analysed using PLS-SEM, while textual data were analysed using Sentence-BERT, BERTopic, semantic network analysis, and Aspect-Based Sentiment Analysis. The results showed that higher AI illiteracy was negatively associated with strategic decision quality and positively associated with automation bias, uncritical trust in AI, and cognitive offloading. Digital proficiency and AI governance awareness weakened the negative association between AI illiteracy and decision quality, while functional-background differences were examined through multigroup analysis. The semantic analysis identified six themes: AI competency, decision trust, AI governance, decision support, organisational learning, and risk awareness. Sentiment analysis showed positive views of productivity and decision support, together with concerns about algorithmic bias, explainability, transparency, and AI governance. The study contributes an integrated human–AI decision vulnerability framework in which semantic evidence complements structural modelling and provides a clearer understanding of AI-related competency, reliance, governance, and decision-support issues. Full article

Background/Objectives: Dental age estimation is important in clinical and forensic practice, particularly when skeletal indicators are unavailable or compromised. Machine-learning models often achieve lower regression errors than conventional dental methods; however, whether this translates into better classification performance at legally relevant age thresholds remains unclear. This study compared the Demirjian and Willems methods with several machine learning models for overall accuracy and threshold-specific performance at the jurisdiction-specific ages of 12 and 15 years. Methods: A total of 1384 panoramic radiographs from individuals aged 8.00–15.99 years were retrospectively evaluated. The developmental stages of the seven left mandibular permanent teeth and sex were used as model inputs. Linear Regression, Decision Tree, Random Forest, Support Vector Regression, Multilayer Perceptron, Gradient Boosting, and XGBoost were trained using cross-validation and evaluated on an internal holdout set. Performance was assessed using regression errors, age-group-specific bias, sensitivity, specificity, balanced accuracy, and likelihood ratios. Results: Machine-learning models generally produced lower errors than conventional methods. In the holdout set, the lowest mean absolute error was 0.512 years for Support Vector Regression and Gradient Boosting, followed by 0.519 years for XGBoost, compared with 0.649 and 0.654 years for the Willems and Demirjian methods. However, lower regression error did not consistently improve threshold-specific performance. At 12 years, machine learning models increased sensitivity but reduced specificity and positive likelihood ratios relative to Willems. At 15 years, Linear Regression and Random Forest produced no positive predictions, whereas the better-performing models showed results similar to Willems. Conclusions: Lower regression error does not necessarily indicate better forensic threshold-specific classification performance. Dental age-estimation models should therefore be validated using threshold-specific likelihood ratios, classification metrics, and age-group-specific bias in addition to overall prediction errors. Full article

High-dimensional environmental covariates are increasingly available for digital soil mapping (DSM), but their effective use depends on both the feature-selection strategy and the predictive model architecture. However, systematic evidence remains limited regarding how different metaheuristic feature-selection methods interact with standalone and hybrid learning models across multiple soil and groundwater prediction tasks. This study systematically evaluated the interactions between 10 metaheuristic feature-selection algorithms and 13 predictive models, including random forest (RF), convolutional neural network (CNN), recurrent architectures, CNN–recurrent neural network (RNN) hybrids, squeeze-and-excitation (SE)-enhanced hybrids, and iTransformer-based hybrids, across four prediction tasks involving soil organic carbon (SOC), soil–water extract electrical conductivity (ECe), apparent electrical conductivity (ECa), and groundwater level (GWL) in Xinjiang, China. A total of 149 candidate environmental covariates were considered for ECe, SOC, and ECa, whereas 122 candidate covariates were considered for GWL. The results showed that no single feature-selection method consistently performed best across all four targets; instead, predictive performance depended on the interaction among the feature-selection strategy, predictive architecture, and target variable. CNN–RNN hybrid architectures generally achieved higher predictive performance than standalone models, although their benefits varied among prediction targets. The best-performing combinations yielded coefficient of determination (R²) values of 0.9826, 0.6981, 0.8429, and 0.8085 for GWL, SOC, ECe, and ECa, respectively. These findings indicate that target-specific compatibility, rather than aggressive dimensionality reduction or a universally superior algorithm, is a key determinant of predictive performance in high-dimensional DSM. By demonstrating that feature-selection effectiveness is jointly influenced by model architecture and target characteristics, this study provides a methodological reference for developing target-specific digital soil mapping models in arid regions. Full article

The Loess Plateau in China is highly susceptible to frequent landslides and other geological disasters, which have led to substantial losses of natural and human resources and are frequently reported in the news media. Yuzhong County, located east of Lanzhou City, is a mountainous region with considerable development potential. On 7 August 2025, this area experienced a large-scale geological disaster characterized by a compound event involving both landslides and debris flows, resulting in nearly several hundred casualties. With the ongoing urban expansion of Yuzhong County in recent years, the prediction and prevention of geological disasters have become increasingly critical. This study employed three machine learning algorithms—Multiple Logistic Regression (LR), Random Forest (RF), and XGBoost (XG)—to assess landslide susceptibility in Yuzhong County. A total of 169 historical landslide points, supplemented by additional sites identified through field investigations, were compiled, along with 200 non-landslide locations. Multiple environmental factors were incorporated into the models to analyze landslide susceptibility across different areas. Because LR can effectively capture the generalized influence of precipitation variability, it was selected as the primary model for the final susceptibility mapping. To more accurately evaluate the impact of precipitation on landslide occurrence, average seasonal precipitation across the four seasons was used as a predictive factor. To refine the risk assessment at the township level, both raster-based and landslide-unit-based evaluation approaches were adopted. Overlay analyses were then performed by integrating urban infrastructure, population distribution, and predicted landslide hazard zones, while also accounting for the potential influence of extreme precipitation events. The results reveal that the mountainous areas in eastern Mapo Township, southern Xiaokangying Township, southern Xiaguanying Town, and the south-central part of Qingshuiyi Township are high-risk zones prone to group-occurrence landslide disasters. Full article

Arabic-speaking populations face disproportionate cybersecurity risks due to the predominantly English-centric design of existing awareness materials, which fail to accommodate Arabic dialectal diversity, script complexity, and culturally embedded communication patterns. These deficiencies impair users’ ability to interpret phishing messages, authentication requests, and security alerts, increasing susceptibility to social engineering, identity theft, and data breaches. This paper presents SECURE-A²RC, a rubric-constrained, Arabic-aware large language model framework designed to deliver scalable, interpretable, and culturally relevant cybersecurity education. The framework comprises two coupled components. The first, the Arabic-Aware Secure Communication Encoder (A-SCE), employs an instruction-tuned LLM to produce multidimensional encodings that capture three learner competencies: security intent comprehension; linguistic deception cue recognition encompassing urgency, authority impersonation, and incentive framing; and action-critical translation fidelity across Arabic dialectal registers and Arabic–English bilingual contexts. The second, the Rubric-Constrained Adaptive Feedback Generator (RCAFG), translates A-SCE encodings into personalized, expert-aligned instructional feedback and proficiency-calibrated adaptive tasks, ensuring pedagogical consistency, security correctness, and dialect awareness throughout the learning cycle. The framework is evaluated on three domain-relevant corpora: the English–Arabic Parallel Phishing Email Corpus, the Open MalSec dataset, and the Arabic Spam and Ham Tweets dataset. SECURE-A²RC achieves a 31% improvement in phishing identification accuracy and a 26% reduction in action-critical translation errors compared to conventional awareness materials. A comparative evaluation against SERENA, a Multi-Agent LLM, and the Arabic Multitask Learning Model confirms consistent superiority across detection accuracy, F1-score, dialectal robustness, and educational effectiveness metrics, affirming rubric-constrained LLM integration as a viable approach to equitable multilingual cybersecurity education. Full article

Cross-scene hyperspectral band selection must reduce spectral redundancy while retaining channels that remain useful beyond the source scene. We propose Adaptive Band Gating (ABG), a source-only selector that combines frequency-domain decoupling enhancement, global and sample-specific gating, source-side spectral, spatial, morphology-inspired, and sensor-noise perturbations, and a dual-head evaluator. The selector is trained with source data and frozen before downstream evaluation. Selected bands are assessed with a radial-basis-function support vector machine on Pavia Center and HyRANK under fixed band budgets and target-label fractions from 0% to 10%. At 5% target labels, 15 selected bands achieve 96.05% overall accuracy on Pavia Center, compared with 95.41% using all 102 bands; 20 selected bands achieve 81.49% on HyRANK, compared with 79.20% using all 176 bands. Across evaluated band budgets, ABG is comparable to XGBS on Pavia Center and provides stronger results on HyRANK. Ablation experiments show that adaptive gating, frequency-domain enhancement, and source-side expansion each contribute to performance. Together, these results demonstrate that ABG learns compact and traceable original-band subsets with strong downstream transfer utility across the evaluated cross-scene settings. Full article

Multi-agent path planning (MAPP) under partial observability requires agents to coordinate their movements and complete tasks efficiently without access to global information. The planning space and coordination complexity grow rapidly with increasing numbers of agents, targets, and obstacles. We formulate large-scale MAPP as a partially observable networked Markov decision process. Based on this formulation, we propose a decentralized model-based Actor-Critic using the Kronecker-factored trust region (DM-ACKTR) algorithm. The algorithm integrates local model learning with ACKTR-based policy optimization in an independent learning architecture. Each agent learns a local model to predict the next observation and reward. These predictions are used to construct additional transitions for Actor and Critic updates. A neighborhood-based communication mechanism incorporates information from nearby agents into value estimation. Region partitioning reduces each agent’s effective planning space. These improvements enable DM-ACKTR to continue outperforming the baseline algorithms as the scale of the MAPP problem increases. Experiments across three training and five evaluation scenarios show that DM-ACKTR achieves the best overall performance. Among the five evaluated algorithms, it consistently obtains the highest TCR and lowest CR, improving TCR by 2.06–4.35% and reducing CR by 11.26–25.95% relative to the respective best baselines. Full article

The rapid advancement of software-defined networking (SDN) has enhanced network programmability, centralized control, and traffic management flexibility, while also increasing exposure to sophisticated attacks targeting the control plane. Although federated learning (FL) enables collaborative intrusion detection without centralized raw data sharing, existing FL-based intrusion detection systems remain vulnerable to plaintext model update leakage, centralized cryptographic trust, limited interpretability, and insufficient validation in operational SDN environments. To address these limitations, this paper presents an explainable federated intrusion detection framework that integrates distributed key generation (DKG), CKKS-based threshold homomorphic encryption, collaborative decryption, and SHapley Additive exPlanations (SHAP). Unlike conventional HE-enabled FL systems that rely on a trusted authority or a globally shared secret key, the proposed framework removes the trusted key-generation dealer, avoids centralized custody of the complete secret key, and prevents any single client or aggregation server from independently decrypting ciphertexts using locally held key material. A gated recurrent unit (GRU)-based model is used for privacy-preserving intrusion detection, and SHAP provides global and local explanations of model decisions. The framework is further deployed in a real-time SDN testbed to evaluate the online inference pipeline following threshold-secured federated training. Computationally intensive cryptographic operations, including DKG, encrypted aggregation, and threshold decryption, are performed during offline training, while the converged global model enables low-latency inference at runtime. Experiments on the InSDN, CICDDoS2017, and CICDDoS2019 datasets with 4, 8, and 12 client federated configurations achieved detection accuracies above 99% across all datasets. The evaluation also examines encryption latency, collaborative decryption overhead, secure aggregation cost, communication complexity, and scalability. The results demonstrate that the proposed framework provides a practical balance among decentralized key management, privacy-preserving aggregation, explainability, detection performance, and real-time SDN deployment feasibility. Full article

Recent advances in robotics have highlighted the importance of multimodal perception for dexterous manipulation in contact-rich environments. Here we present BiTAT, a bimanual tactile-augmented teleoperation system for collecting multimodal human demonstrations and learning manipulation policies. The system integrates custom capacitive tactile sensors into parallel grippers and displays the resulting contact-deformation images to the operator. We evaluated the system in four controlled laboratory tasks: USB removal/insertion, bottle cap unscrewing, cucumber peeling, and toothpaste squeezing. In a pilot repeated-measures study with eight laboratory participants, visual tactile feedback was associated with success-rate increases of 12.5–32.5 percentage points and shorter completion times among successful trials. We further propose a multimodal Diffusion Policy that fuses visual, tactile, and proprioceptive features through a Transformer encoder. In two fixed-layout autonomous tasks, the complete model achieved higher observed success rates than the vision-only baseline, including a 45-percentage-point difference in the 50-demonstration toothpaste-squeezing setting. Together, these results demonstrate the feasibility of the proposed hardware–policy pipeline and suggest that tactile augmentation benefits both human teleoperation and learned manipulation policies in contact-rich tasks. Full article

Learning from feedback depends not only on the feedback provided but also on how learners interpret, evaluate, and respond to it. This descriptive phenomenological study explored how preclinical medical students experienced receiving peer evaluation in a team-based learning (TBL) course. Forty-one reflective journals written by first-year medical students (27 men, 14 women) after receiving anonymous peer feedback were analyzed using Colaizzi’s seven-step descriptive phenomenological method. Five interrelated themes emerged: preparing to contribute, encountering oneself through peers’ eyes, making sense of emotional responses, transforming feedback into future practice, and becoming a responsible evaluator. Students described peer feedback as a social mirror that revealed differences between their self-perceptions and those of their peers. They reported a range of emotional responses and also reflected on the credibility and relevance of the feedback they received. Many students expressed intentions for future participation, and some reflected on their own responsibilities as evaluators. Taken together, the accounts described self-reflection, emotional appraisal, and intentions for future participation after peer evaluation. The findings suggest that peer evaluation accompanied by open-ended reflection may provide a useful context for examining how students experience and make sense of feedback. Whether such reflection contributes to subsequent changes in behavior, feedback literacy, self-regulated learning, or professionalism requires further study. Full article

Promoting morality among youth is an important educational priority in Thailand’s Southern Border Provinces. However, few culturally grounded learning interventions based on the Sufficiency Economy Philosophy have been systematically developed and evaluated. This study aimed to develop and preliminarily evaluate the Digital Learning Innovation for Strengthening Society (DLISS), a culturally grounded learning intervention designed to promote self-reported morality among youth. A four-phase research and development design was employed, including needs assessment, intervention and instrument development, preliminary field implementation, and post-implementation expert appraisal. Self-reported morality was assessed using the Sufficiency Economy Moral Scale (SEMS), which underwent psychometric evaluation with 1640 youth. Preliminary implementation involved 22 youth leaders assessed at pretest, immediate posttest, and post-reinforcement assessment. The SEMS demonstrated satisfactory psychometric properties. Participants showed statistically significant within-participant changes in the five measured dimensions of self-reported morality across the three assessment occasions. Experts rated the DLISS model favorably for its appropriateness, feasibility, utility, and contextual relevance. The DLISS model represents a promising culturally grounded learning intervention for promoting self-reported morality among youth. The findings provide preliminary evidence supporting further evaluation using larger samples and controlled research designs. Full article