Search Results (976)

A personalized framework for smart home automation is introduced, utilizing machine learning to predict user activities and allow for the context-aware control of living spaces. Predicting user activities, such as ‘Watch_TV’, ‘Sleep’, ‘Work_On_Computer’, and ‘Cook_Dinner’, is essential for improving occupant comfort, optimizing energy consumption, and offering proactive support in smart home settings. The Edge Light Human Activity Recognition Predictor, or EL-HARP, is the main prediction model used in this framework to predict user behavior. The system combines open-source software for real-time sensing, facial recognition, and appliance control with affordable hardware, including the Raspberry Pi 5, ESP32-CAM, Tuya smart switches, NFC (Near Field Communication), and ultrasonic sensors. In order to predict daily user activities, three gradient-boosting models—XGBoost, CatBoost, and LightGBM (Gradient Boosting Models)—are trained for each household using engineered features and past behaviour patterns. Using extended temporal features, LightGBM in particular achieves strong predictive performance within EL-HARP. The framework is optimized for edge deployment with efficient training, regularization, and class imbalance handling. A fully functional prototype demonstrates real-time performance and adaptability to individual behavior patterns. This work contributes a scalable, privacy-preserving, and user-centric approach to intelligent home automation. Full article

AI chatbots have the potential to facilitate students’ academic progress and enhance knowledge accessibility in higher education, yet learners’ attitudes toward these technologies vary amid AI-driven disruptions, with factors influencing acceptance remaining debated. The current study constructs an integrated model based on Technology Acceptance Model 3 (TAM3), an extension of the original TAM, incorporating factors including Self-Efficacy, Perceived Enjoyment, Anxiety, Perceived Ease of Use, Perceived Usefulness, Output Quality, Social Influence, and Behavioral Intention, to explore determinants and mechanisms influencing learners’ acceptance of AI chatbots. This addresses key challenges in AI-augmented learning, such as personalization benefits versus risks like information inaccuracy and ethical concerns. Results from the questionnaire survey analysis with 265 valid responses reveal significant relationships: (1) self-efficacy significantly predicts perceived ease of use; (2) both perceived enjoyment and perceived ease of use positively influence perceived usefulness; and (3) self-efficacy, perceived usefulness, and social influence collectively exert significant effects on behavioral intention. Measurement invariance tests further indicate significant differences in acceptance between undergraduate and graduate students, suggesting academic level moderates behavioral intentions. Findings offer principled guidance for designing inclusive AI tools that mitigate accessibility barriers and promote equitable adoption in educational environments. Full article

Distance learning has become essential to higher education, yet its application in military officer training presents unique academic, operational, and security challenges. For Lithuania’s future officers, remote education must foster not only knowledge acquisition but also decision-making, leadership, and operational readiness—competencies traditionally developed in immersive, in-person environments. This study addresses these challenges by integrating System Dynamics Modelling, Contemporary Risk Management Standards (ISO 31000:2022; Dynamic Risk Management Framework), and Learning Analytics to evaluate the interdependencies among twelve critical factors influencing the system resilience and effectiveness of distance military education. Data were collected from fifteen domain experts through structured pairwise influence assessments, applying the fuzzy DEMATEL method to map causal relationships between criteria. Results identified key causal drivers such as Feedback Loop Effectiveness, Scenario Simulation Capability, and Predictive Intervention Effectiveness, which most strongly influence downstream outcomes like learner engagement, risk identification, and instructional adaptability. These findings emphasize the strategic importance of upstream feedback, proactive risk planning, and advanced analytics in enhancing operational readiness. By bridging theoretical modelling, contemporary risk governance, and advanced learning analytics, this study offers a scalable framework for decision-making in complex, high-stakes education systems. The causal relationships revealed here provide a blueprint not only for optimizing military distance education but also for enhancing overall system resilience and adaptability in other critical domains. Full article

Following the significant disruption of traditional teaching by the COVID-19 pandemic, gamified education—an approach integrating technology and cognitive strategies—has gained widespread attention and use among educators and learners. This study explores how game-based learning, supported by situated learning theory and game design elements, can boost learner motivation and knowledge construction. Using 20,293 user comments from the Chinese video platform Bilibili, the study applies sentiment analysis and LDA to uncover users’ sentimental tendencies and cognitive themes. The analysis identifies four core themes: (1) The application of contextual strategies in language learning, (2) Autonomous exploration and active participation in gamified learning, (3) Progressive enhancement of logical thinking in gamified environments, and (4) Teaching innovation in promoting knowledge construction and deepening. Building on these findings, the study further develops a cognitive scaffolding model integrating “contextualization–procedural logic–active construction” to explain the mechanisms of motivation–cognition interaction in gamified learning. Methodologically, this study innovatively combines LDA topic modeling with sentiment analysis, offering a new approach for multidimensional measurement of learner attitudes in gamified education. Theoretically, it extends the application of situated learning theory to digital education, providing systematic support for instructional design and meaning-making. Findings enrich empirical research on gamified learning and offer practical insights for optimizing educational platforms and personalized learning support. Full article

This paper introduces CodeDive, a web-based programming environment with real-time behavioral tracking designed to enhance student progress assessment and provide timely support for learners, while also addressing the academic integrity challenges posed by Large Language Models (LLMs). Visibility into the student’s learning process has become essential for effective pedagogical analysis and personalized feedback, especially in the era where LLMs can generate complete solutions, making it difficult to truly assess student learning and ensure academic integrity based solely on the final outcome. CodeDive provides this process-level transparency by capturing fine-grained events, such as code edits, executions, and pauses, enabling instructors to gain actionable insights for timely student support, analyze learning trajectories, and effectively uphold academic integrity. It operates on a scalable Kubernetes-based cloud architecture, ensuring security and user isolation via containerization and SSO authentication. As a browser-accessible platform, it requires no local installation, simplifying deployment. The system produces a rich data stream of all interaction events for pedagogical analysis. In a Spring 2025 deployment in an Operating Systems course with approximately 100 students, CodeDive captured nearly 25,000 code snapshots and over 4000 execution events with a low overhead. The collected data powered an interactive dashboard visualizing each learner’s coding timeline, offering actionable insights for timely student support and a deeper understanding of their problem-solving strategies. By shifting evaluation from the final artifact to the developmental process, CodeDive offers a practical solution for comprehensively assessing student progress and verifying authentic learning in the LLM era. The successful deployment confirms that CodeDive is a stable and valuable tool for maintaining pedagogical transparency and integrity in modern classrooms. Full article

The scarcity of explicit feedback data is a major challenge in the design of recommender systems. Although such data are of a high quality due to users’ voluntary provision of numerical ratings, collecting a sufficient amount in real-world service environments is typically infeasible. As an alternative, implicit feedback data are extensively used. However, because implicit feedback represents observable user actions rather than direct preference statements, it inherently suffers from ambiguity as a signal of true user preference. To address this issue, this study reinterprets the ambiguity of implicit feedback signals as a problem of epistemic uncertainty regarding user preferences and proposes a latent factor model that incorporates this uncertainty within a Bayesian framework. Specifically, the behavioral vector of a user, which is learned from implicit feedback, is restructured within the embedding space using attention mechanisms applied to the user’s interaction history, forming an implicit preference representation. Similarly, item feature vectors are reinterpreted in the context of the target user’s history, resulting in personalized item representations. This study replaces the deterministic attention scores with stochastic attention weights treated as random variables whose distributions are modeled using a Bayesian approach. Through this design, the proposed model effectively captures the uncertainty stemming from implicit feedback within the vector representations of users and items. The experimental results demonstrate that the proposed model not only effectively mitigates the ambiguity of preference signals inherent in implicit feedback data but also achieves better performance improvements than baseline models, particularly on datasets characterized by high user–item interaction sparsity. The proposed model, when integrated with an attention module, generally outperformed other MLP-based models in terms of NDCG@10. Moreover, incorporating the Bayesian attention mechanism yielded an additional performance gain of up to 0.0531 compared to the model using a standard attention module. Full article

Non-traditional learners comprise approximately 73% of undergraduate enrollment, representing diverse populations including first-generation college students, adult learners, veterans, multilingual learners, and students with family responsibilities. Despite their numerical dominance, these students face systemic barriers that traditional pedagogical approaches often fail to address. This mixed-methods study examined how Universal Design for Learning (UDL) principles impact non-traditional learners’ educational experiences in higher education. Using a convergent parallel design with 154 participants from a Hispanic-serving institution, the study collected quantitative data through the validated Personalized Learning Supporting Instrument (PLSI) and qualitative data from open-ended questions. The refined 12-item PLSI demonstrated strong psychometric properties. While UDL factors showed limited direct association with GPA overall, Flexible Instructional Methods and Materials significantly predicted academic performance. Qualitative analysis identified six barrier themes (online learning difficulties, course content issues, financial constraints, balancing responsibilities, accessibility challenges, and health interruptions) and five positive impact themes (interactive learning, supportive environments, skill development, goal clarification, and effective assignments). Demographic analysis revealed counterintuitive patterns—students with traditional “barriers” achieved high GPAs at rates of 73–76%, while first-generation students showed the lowest high GPA rate (53.2%). These findings challenge deficit-based assumptions about non-traditional learners while revealing important equity gaps. This study demonstrates both the promise and limitations of UDL for diverse populations, suggesting institutions need comprehensive approaches with differentiated support strategies. Full article

In a world where artificial intelligence is constantly changing education, taking students’ feelings into account is a crucial framework for enhancing their engagement and academic performance. This article presents LearnerEmotions, an online application that employs machine vision technology to determine how learners are feeling in real time through their facial expressions. Teachers and institutions can access analytical dashboards and monitor students’ emotions with this tool, which is designed for use in both in-person and remote classes. The facial expression recognition model used in this application achieved an average accuracy of 0.91 and a loss of 0.3 in the real environment. More than 9 million emotional data points were gathered from an experiment involving 65 computer engineering students, and these insights were correlated with attendance and academic performance. While negative emotions like anger, sadness, and fear are associated with decreased performance and lower attendance, the statistical study shows a strong correlation between positive feelings like surprise and joy and successful academic performance. These results underline the necessity of technological tools that offer immediate pedagogical regulation and support the notion that emotions play an important role in the learning process. Thus, LearnerEmotions, which considers students’ emotional states, is a potential first step toward more adaptive learning. Full article

The increasing integration of artificial intelligence into educational processes offers new opportunities to address critical issues in higher education, such as student dropout, academic underperformance, and the need for personalized tutoring. This scoping review aims to map the scientific literature on the use of AI techniques to predict academic performance, risk of dropout, and the need for academic advising, with an emphasis on e-learning or technology-mediated environments. The study follows the Joanna Briggs Institute PCC strategy, and the review was reported following the PRISMA-ScR checklist for search reporting. A total of 63 peer-reviewed empirical studies (2019–2025) were included after systematic filtering from the Scopus and Web of Science databases. The findings reveal that supervised machine learning models, such as decision trees, random forests, and neural networks, dominate the field, with an emerging interest in deep learning, transfer learning, and explainable AI. Academic, behavioral, emotional, and contextual variables are integrated into increasingly complex and interpretable models. Most studies focus on undergraduate students in digital and hybrid learning contexts, particularly in regions with high dropout rates. The review highlights the potential of AI to enable early intervention and improve the effectiveness of tutoring systems, while noting limitations such as lack of model generalization and ethical concerns. Recommendations are provided for future research and institutional integration. Full article

Multiple sclerosis (MS) is a chronic, immune-mediated neurodegenerative disorder marked by inflammation, demyelination, and neuronal loss within the central nervous system. Despite advances in diagnostics, current tools remain insufficiently sensitive and specific. Metabolomics has emerged as a promising approach to explore MS pathophysiology and discover novel biomarkers. This PRISMA-guided systematic review included 29 original studies using validated metabolomic techniques in adult patients with MS. Biological samples analyzed included serum, cerebrospinal fluid, and feces. Consistent metabolic alterations were identified across several pathways. The kynurenine pathway demonstrated a shift toward neurotoxic metabolites, alongside reductions in microbial-derived indoles, indicating inflammation and gut dysbiosis. Energy metabolism was impaired, with changes in glycolysis, tricarboxylic acid (TCA) cycle, and mitochondrial function. Lipid metabolism showed widespread dysregulation involving phospholipids, sphingolipids, endocannabinoids, and polyunsaturated fatty acids, some modulated by treatments such as ocrelizumab and interferon-β. Nitrogen metabolism was also affected, including amino acids, peptides, and nucleotides. Non-classical and xenobiotic metabolites, such as myo-inositol, further reflected host–microbiome–environment interactions. Several studies demonstrated the potential of metabolomics-based machine learning to distinguish MS subtypes. These findings highlight the value of metabolomics for biomarker discovery and support its integration into personalized therapeutic strategies in MS. Full article

This article explores how gender biases in STEM education persist despite formal commitments to equality. Based on data from the Erasmus+ project STEMGenderIN, we analyze responses from lower-secondary school teachers (ISCED 2; ages 11–15), of STEM subjects, in Portugal, Italy, Belgium, and Romania using the TPGESE scale, which assesses three dimensions: perceived gender equality in education (PGEE), the awareness of the effects of gender segregation (AEGSE), and the naturalization of gender stereotypes (GSNGI). Findings show a consistent gap between teachers declared support for gender equality and their limited awareness of structural and cultural barriers faced by girls in STEM. While most teachers affirm equality in principle, many attribute girls’ underrepresentation to personal choice or aptitude, overlooking the influence of stereotypes, social expectations, and systemic inequalities. The results point to a paradox: formal recognition of gender equality coexists with low engagement in reflexive practice or institutional change. Differences between countries suggest varying degrees of critical awareness, with some contexts showing greater openness to questioning dominant narratives. This study highlights the urgent need for teacher training that goes beyond rhetoric, promoting deep pedagogical transformation and equipping educators to create more inclusive STEM learning environments. We argue that addressing the perception–practice gap is essential to closing the gender gap in STEM. To situate these findings, we also note how national cultural–political debates—such as Portugal’s public controversy around so-called “gender ideology” in Citizenship and Development—may shape teachers’ perceptions and self-reports, reinforcing the need for context-aware training. Full article

Personalized education, particularly for gifted students, has attracted increasing attention as digital tools expand opportunities to adapt learning to individual students’ needs, interests, and abilities. However, the conceptual ambiguity surrounding personalization, which is often conflated with differentiation or individualization, calls for a clearer understanding of its implementation in digital environments. This study presents a systematic literature review of research published between 2000 and 2024 on digital tools for the personalized education of gifted students. Following the PRISMA guidelines, a comprehensive search was conducted in SCOPUS and Web of Science, yielding 257 initial records. After applying inclusion and exclusion criteria, a final corpus of 55 studies was analyzed through temporal, geographic, educational, and curricular perspectives. Thematic coding was also applied. The results show a marked increase in publications after 2020, with the United States and Russia as leading contributors, and a predominant focus on secondary education and STEM/STEAM disciplines. Across studies, digital tools were found to support personalization by fostering autonomy, creativity, collaboration, and advanced cognitive skills, though significant challenges remain in terms of equity, teacher training, and data security. Following this review, we conclude that although digital tools hold substantial promise for advancing personalized learning, their broader implementation requires integrative and context-sensitive strategies. Full article

Brain–computer interfaces (BCIs) hold promise in enhancing accessibility in education by enabling students with physical disabilities to interact with digital learning environments without barriers. However, no comprehensive review has explored the landscape and role of BCIs in inclusive learning. Hence, this review sets out to identify relevant literature on BCI-based educational technologies, highlight their key themes, characteristics, and research methodologies, and identify research gaps. The secondary aim is to evaluate how these educational technologies contribute to inclusive learning frameworks by fostering communication, collaboration, engagement, and accessibility among students with disabilities. Overall, the reviewed studies demonstrate that BCIs can facilitate assistive communication among non-verbal students and provide motor control support for physically impaired persons. While these interventions show strong potential, challenges remain, including high implementation costs, user adaptability, and ethical concerns related to neural data privacy. Specifically, there is a need to (1) shift from experimental applications towards real-world classroom integration by developing user-friendly, cost-effective, and ethically sound BCI-based educational technologies, and (2) extend ongoing research efforts to include underserved populations to assess the generalizability of current and future BCI-based interventions. More importantly, future work should focus on enhancing BCI usability, improving adaptability for diverse learners, and establishing ethical guidelines for the development of socially responsible and inclusive neuro-educational technologies for all people with disabilities everywhere. This will go a long way in fostering the fourth and tenth United Nations Sustainable Development Goals of Quality Education and Reduced Inequalities, respectively. Full article

In large-scale recommendation scenarios, achieving high-precision ranking requires simultaneously modeling user interest dynamics and content propagation potential. In this work, we propose a unified framework that integrates a temporal interest modeling stream with a multimodal virality encoder. The temporal stream captures sequential user behavior through the self-attention-based modeling of long-term and short-term interests, while the virality encoder learns latent virality factors from heterogeneous modalities, including text, images, audio, and user comments. The two streams are fused in the ranking layer to form a joint representation that balances personalized preference with content dissemination potential. To further enhance efficiency, we design hierarchical cascade heads with gating recursion for progressive refinement, along with a multi-level pruning and cache management strategy that reduces redundancy during inference. Experiments on three real-world datasets (Douyin, Bilibili, and MIND) demonstrate that our method achieves significant improvements over state-of-the-art baselines across multiple metrics. Additional analyses confirm the interpretability of the virality factors and highlight their positive correlation with real-world popularity indicators. These results validate the effectiveness and practicality of our approach for high-precision recommendation in big data environments. Full article

This research article explores the integration of Buddhist and philosophical principles into educational methodologies to enhance learning skills. The objectives were to develop a creative educational model, identify key factors influencing learning skills, and assess the approach’s effectiveness. The study targeted students from higher education institutions as the population. A purposive sampling technique was employed, selecting participants who demonstrated an interest in or familiarity with Buddhist teachings and philosophical inquiry. The research employed a mixed-methods approach, combining qualitative and quantitative data collection techniques. Tools included questionnaires/surveys, semi-structured interview questions, and observations, supplemented by focus group discussions and thematic analyses and a suitability and feasibility evaluation form. The analyses were performed using Principal Component Analysis (PCA), content analysis, theme analysis, and data saturation. Statistics were in the form of percentages, means, SDs, t-values, and exploratory factor analyses (EFA). The results indicated that integrating Buddhist practices, such as mindfulness and reflective thinking, with philosophical methods, such as critical inquiry and dialogue, significantly improved students’ cognitive, emotional, and ethical development. Key findings highlighted the importance of fostering an environment encouraging open-mindedness, self-reflection, and ethical reasoning. The study’s significance lies in its contribution to educational innovation, providing a framework for integrating spiritual and philosophical dimensions into contemporary education. This approach enhances traditional academic skills and promotes holistic development, preparing students for personal and societal challenges. Full article