Search Results (244)

The knowledge tracing method based on deep learning is used to assess learners’ cognitive states, laying the foundation for personalized education. However, deep learning methods are inefficient when processing long-term series data and are prone to overfitting. To improve the accuracy of cognitive state prediction, we design a Multi-layer Attention Self-supervised Knowledge Tracing Method (MASKT) using self-supervised learning and the Transformer method. In the pre-training stage, MASKT uses a random forest method to filter out positive and negative correlation feature embeddings; then, it reuses noise-processed restoration tasks to extract more learnable features and enhance the learning ability of the model. The Transformer in MASKT not only solves the problem of long-term dependencies between input and output using an attention mechanism, but also has parallel computing capabilities that can effectively improve the learning efficiency of the prediction model. Finally, a multidimensional attention mechanism is integrated into cross-attention to further optimize prediction performance. The experimental results show that, compared with various knowledge tracing models on multiple datasets, MASKT’s prediction performance remains 2 percentage points higher. Compared with the multidimensional attention mechanism of graph neural networks, MASKT’s time efficiency is shortened by nearly 30%. Due to the improvement in prediction accuracy and performance, this method has broad application prospects in the field of cognitive diagnosis in intelligent education. Full article

While personal thermal comfort is critical for well-being and productivity, it is often overlooked by traditional building management systems that rely on uniform settings. Modern data-driven approaches often fail to capture the complex interactions between various data streams. This pilot study introduces a high-accuracy, interpretable framework for thermal comfort classification, designed to identify the most significant predictors from a comprehensive suite of environmental, physiological, and anthropometric data in a controlled group of young adults. Initially, an XGBoost model using the full 24-feature dataset achieved the best performance at 91% accuracy. However, after using SHAP analysis to identify and select the most influential features, the performance of our ensemble models improved significantly; notably, a Random Forest model’s accuracy rose from 90% to 94%. Our analysis confirmed that for this homogeneous cohort, environmental parameters—specifically temperature, humidity, and CO₂—were the dominant predictors of thermal comfort. The primary strength of this methodology lies in its ability to create a transparent pipeline that objectively identifies the most critical comfort drivers for a given population, forming a crucial evidence base for model design. The analysis also revealed that the predictive value of heart rate variability (HRV) diminished when richer physiological data, such as diastolic blood pressure, were included. For final validation, the optimized Random Forest model, using only the top 10 features, was tested on a hold-out set of 100 samples, achieving a final accuracy of 95% and an F1-score of 0.939, with all misclassifications occurring only between adjacent comfort levels. These findings establish a validated methodology for creating effective, context-aware comfort models that can be embedded into intelligent building management systems. Such adaptive systems enable a shift from static climate control to dynamic, user-centric environments, laying the critical groundwork for future personalized systems while enhancing occupant well-being and offering significant energy savings. Full article

In the digital communication ecosystem, micro-influencers have influenced public response during crises, especially in complex geopolitical contexts. This paper introduces the micro-influencer impact model (MIIM), a framework for analyzing the impact of micro-influencers on crisis communication. The MIIM integrates four components (micro-influencer characteristics, message framing and delivery, audience factors, and crisis context) offering a comprehensive approach to understanding micro-influencer dynamics during crises. Cross-conflict analysis spanning Ukraine–Russia, Sudan–Ethiopia, Armenia–Azerbaijan, Myanmar, Syria, and India–Pakistan tensions demonstrates the MIIM’s broad applicability across diverse geopolitical crises, showing how factors like perceived authenticity, niche expertise, narrative personalization, and audience digital literacy consistently shape public opinion and crisis response. The MIIM synthesizes crisis communication theories, social influence models, and digital media research, providing a sophisticated framework for studying the dissemination of information and public engagement during crises. The paper proposes theoretically grounded propositions on the impact of micro-influencers, encompassing perceived authenticity, narrative framing, and influence over time, thereby laying the groundwork for future empirical research. Implications for communication scholars, crisis managers, policymakers, and social media platforms are discussed, emphasizing the MIIM’s relevance to theory and practice in crisis communication. Full article

Background/Objectives: Electronic medical record systems play a crucial role in the operation of modern healthcare institutions, enabling the foundational data necessary for advancements in personalized medicine. Despite their importance, the software supporting these systems frequently experiences data availability and integrity issues, particularly concerning patients’ personal information. This study aims to present a decentralized architecture that integrates both clinical and personal patient data, with a provenance mechanism to enable data tracing and auditing, ultimately supporting more precise and personalized healthcare decisions. Methods: A system implementation based on the solution was developed, and a feasibility study was conducted with synthetic medical records data. Results: The system was able to correctly receive data of 190 instances of the entities designed, which included different types of medical records, and generate 573 provenance entries that captured in detail the context of the associated medical information. Conclusions: For the first cycle of the research, the system developed served to validate the main features of the solution, and through that, it was possible to infer the feasibility of a decentralized EHR and PHR health system with formal provenance data tracking. Such a system lays a robust foundation for secure and reliable data management, which is essential for the effective implementation and future development of personalized medicine initiatives. Full article

The integration of artificial intelligence (AI) into education requires frameworks that are not only technically robust but also ethically and pedagogically grounded. This paper proposes the Generalist Education Artificial Intelligence (GEAI) framework—a conceptual blueprint designed to enable privacy-preserving, personalized, and multimodal AI-supported learning in educational contexts. GEAI features a Trusted Domain architecture that supports secure, voluntary multimodal data collection via multimedia registration devices (MM Devices), edge-based AI inference, and institutional data sovereignty. Drawing on principles from constructivist pedagogy and regulatory standards such as GDPR and FERPA, GEAI supports adaptive feedback, engagement monitoring, and learner-centered interaction while addressing key challenges in ethical data governance, transparency, and accountability. To bridge theory and application, we outline a staged validation roadmap informed by technical feasibility assessments and stakeholder input. This roadmap lays the foundation for future prototyping and responsible deployment in real-world educational settings, positioning GEAI as a forward-looking contribution to both AI system design and education policy alignment. Full article

In higher education, the emotional intelligence (EI) of university professors, defined as the ability to perceive, understand, manage and utilize emotions effectively, is increasingly recognized as a pivotal factor in enhancing students’ academic achievement and psychological well-being. However, the scarcity of studies directly linking professors’ EI to students’ well-being highlights a critical research gap. This systematic review investigates how professors’ emotional competencies influence student outcomes—such as academic performance, engagement, motivation, and mental health—and identifies the factors that mediate or moderate these effects. Findings indicate that professors’ EI, particularly empathy, emotional regulation, and interpersonal skills, significantly enhances student engagement, motivation, and academic satisfaction, with indirect effects on psychological well-being. Cultural context, teaching modality (e.g., online vs. in-person), and professors’ age and experience moderate these effects and influence effect sizes. Qualitative synthesis further highlighted contextual gaps in the literature. The limited focus on well-being and outcomes and reliance on self-report measures underscore the need for longitudinal, culturally diverse studies and performance-based EI assessments. The value of this research lies in its potential to inform evidence-based educational practices and institutional policies. By elucidating the role of professors’ EI, the review lays the groundwork for developing faculty training programs aimed at strengthening emotional competencies and fostering inclusive, supportive learning environments that promote student growth and resilience. This is especially relevant given the growing prevalence of stress, anxiety, and disengagement among university students, exacerbated by post-pandemic challenges and academic pressures. Understanding the impact of EI can inform culturally responsive interventions, improve student retention, and enhance institutional effectiveness, thereby addressing a pressing need in contemporary higher education. In today’s rapidly evolving technological, social, and cultural landscape, universities have both the opportunity and the responsibility to act as catalysts for the creation of an educational culture that promotes social well-being. This requires adopting educational and organizational models that prioritize human care and the quality of interpersonal relationships. To be effective, these priorities must be integrated into all university operations, from governance to student support and talent development. Full article

Spinal cord injury (SCI) is a severe neurological condition that typically results in irreversible loss of motor and sensory function. Emerging evidence indicates that neuroplasticity, the ability of the nervous system to reorganize by forming new neural connections, plays a pivotal role in structural and functional recovery post-injury. This insight lays the groundwork for the development of rehabilitation and therapeutic strategies designed to leverage neuroplasticity. In this review, we offer an exhaustive overview of the neuroplastic alterations and mechanisms that occur following an SCI. We examine the role of neuroplasticity in functional recovery and outline therapeutic approaches designed to augment neuroplasticity post-SCI. The process of neuroplasticity post-SCI involves several physiological processes, such as neurogenesis, synaptic remodeling, dendritic spine formation, and axonal sprouting. Together, these processes contribute to the reestablishment of neural circuits and functional restoration. Enhancing neuroplasticity is a promising strategy for improving functional outcomes post-SCI; however, its effectiveness is influenced by numerous factors, including age, injury severity, time since the injury, and the specific therapeutic interventions employed. A variety of strategies have been suggested to promote neuroplasticity and expedite recovery, including pharmacological treatments, biomaterial-based therapies, gene editing, stem cell transplantation, and rehabilitative training. The combination of personalized rehabilitation programs with innovative therapeutic techniques holds considerable potential for maximizing the benefits of neuroplasticity and enhancing clinical outcomes in SCI management. Full article

The demeanour of a human during an interaction with an animal may influence the animal’s emotional response. We investigated whether the emotional responses of laying hens to a threatening or neutral human and a novel environment were lateralised, from which their emotional state can be inferred. Twenty-five DeKalb white laying hens reared in furnished cages under environmentally controlled conditions were individually assessed for their responses to these stimuli. They were contained in a box before emerging into an arena with a threatening human, who attempted direct eye contact with the bird and had their hands raised towards it, or a neutral person, who had no eye contact and sat with their hands on their knees. When initially placed in the box adjacent to the test arena, birds that remained in the box used their left eye more than their right eye, and they showed evidence of nervousness, with many head changes, neck stretching, and vocalisation. Birds showed lateralised behaviour in both the box and arena. Birds entering the arena with the threatening person used their left eye (connected to the right brain hemisphere) more than their right eye, usually with their body less vertical, and were more likely to be standing than sitting, compared with those viewing the neutral person. This confirms the bird’s interpretation of the person as threatening, with left eye/right brain hemisphere processing of flight or fight situations. We conclude that lateralised responses of chickens suggest that a threatening person is viewed more fearfully than a neutral person. However, further investigation is required with a larger sample of birds to strengthen these findings and enhance the generalisability of behavioural responses. Full article

This paper analyses the religious experience of young people in contexts of digitalisation. The secularisation thesis has not been imposed. Youth, who are more open to the porosity of social and cultural boundaries, live outside of dogma and the church, with the signs of transcendence as a fundamental part of their personal narrative. Religiosity, a contingent temporality, and youth socialised in the unknown lay the foundations for this reflection. Full article

Objectives: The quantitative analysis of tumor progression—monitored during and immediately after therapeutic interventions—can yield valuable insights into both long-term disease dynamics and treatment efficacy. Methods: We used a computational approach designed to support clinical decision-making, with a focus on personalized patient care, based on modeling therapy effects using effective parameters of the Gompertz law. Results: The method is applied to data from in vivo models undergoing neoadjuvant chemoradiotherapy, as well as conventional and FLASH radiation treatments. Conclusions: This user-friendly, phenomenological model captures distinct phases of treatment response and identifies a critical dose threshold distinguishing complete response from partial response or tumor regrowth. These findings lay the groundwork for real-time quantitative monitoring of disease progression during therapy and contribute to a more tailored and predictive clinical strategy. Full article

This study presents a system for automatic cookie collection using bots that simulate user browsing behavior. Five bots were deployed, one for each of the most commonly used university browsers, enabling comprehensive data collection across multiple platforms. The infrastructure included an Ubuntu server with PiHole and Tshark services, facilitating cookie classification and association with third-party advertising and tracking networks. The BotSoul algorithm automated navigation, analyzing 440,000 URLs over 10.9 days with uninterrupted bot operation. The collected data established relationships between visited domains, generated cookies, and captured traffic, providing a solid foundation for security and privacy analysis. Machine learning models were developed to classify suspicious web domains and predict their vulnerability to XSS attacks. Additionally, clustering algorithms enabled user segmentation based on cookie data, identification of behavioral patterns, enhanced personalized web recommendations, and browsing experience optimization. The results highlight the system’s effectiveness in detecting security threats and improving navigation through adaptive recommendations. This research marks a significant advancement in web security and privacy, laying the groundwork for future improvements in protecting user information. Full article

Background: Associations between high physical activity (PA) levels and incident atrial fibrillation (AF) is found in some earlier studies. We aim to study the association between levels of PA and AF in two cohorts. Methods: We used data from the Uppsala Longitudinal Study of Adult Men (ULSAM) study, initiated in 1970, included men aged 50 years, with 2202 included in the study. Examinations were reiterated three times, with follow-up after in median 33 years, with 3.8–6.0% on the highest PA level. We also used data from the Prospective Investigation of the Vasculature in Uppsala Seniors (PIVUS; with women 50%); mean age 70 years, baseline 2001–2004, median follow-up 15 years, with 961 included in the study, with 4.8% on the highest PA level. Cox regression analysis with hazard ratios (HRs) was used to study association between PA levels and incident AF, adjusted for CV risk factors: systolic blood pressure, LDL- and HDL-cholesterol, BMI, diabetes, and smoking. Results: Totally, in ULSAM 504 men during 59,958 person-years at risk, and in PIVUS 204 individuals during a follow-up of 11,293 person-years experienced an AF. Neither in ULSAM, PIVUS, nor in the meta-analysis of both cohorts, individuals with the highest PA level showed an increased AF risk, compared to individuals with lowest level of PA. Conclusions: The benefits of PA in community dwelling individuals for its benefits to mental, metabolic, and cardiovascular health should guide public recommendations, rather than a possible risk of AF. Lay Summary: We studied the risk of incident atrial fibrillation at various levels of physical activity in two cohorts and found no statistically significant increased risk after adjusting for cardiovascular risk factors (systolic blood pressure, LDL- and HDL-cholesterol, BMI, diabetes, and smoking). Full article

The COVID-19 pandemic and the resulting stay-at-home orders disrupted religious life across the United States, forcing congregations to rapidly adapt to unprecedented challenges. While existing research has explored the pandemic’s impact on individual religiosity, this article centers on how congregations were reshaped by the pandemic—sometimes temporarily, sometimes permanently. Drawing on nationally representative survey data from the Exploring the Pandemic Impact on Congregations project and the long-running Faith Communities Today initiative, this article analyzes trends in worship attendance, other forms of commitment to and engagement with congregations, congregational openness to change, and clergy well-being. The findings show that in-person worship attendance continues to decline, while online worship was adopted widely during the pandemic and remains common. Programming, volunteering, and financial giving have rebounded but still fall short of pre-pandemic levels or current needs. Many congregations embraced change early in the pandemic but have since reverted to old routines. Clergy are in relatively good health, yet growing numbers are reconsidering their futures in ministry. These shifts reveal the pandemic’s lasting impact on congregational life and raise critical questions for clergy, lay leaders, and researchers about institutional resilience, innovation, and leadership sustainability. The findings underscore the complex and evolving nature of post-pandemic ministry. Full article

Proactively detecting schizophrenia relapse remains a critical challenge in psychiatric care, where traditional predictive models often fail to capture the complex neurophysiological and behavioral dynamics preceding recurrence. Existing methods typically rely on shallow architectures or unimodal data sources, resulting in limited sensitivity—particularly in the early stages of relapse. In this study, we propose a CNN-Transformer fusion model that leverages the complementary strengths of Convolutional Neural Networks (CNNs) and Transformer-based architectures to process electroencephalogram (EEG) signals enriched with clinical and sentiment-derived features. This hybrid framework enables joint spatial-temporal modeling of relapse indicators, allowing for a more nuanced and patient-specific analysis. Unlike previous approaches, our model incorporates a multi-resource data fusion pipeline, improving robustness, interpretability, and clinical relevance. Experimental evaluations demonstrate a superior prediction accuracy of 97%, with notable improvements in recall and F1-score compared to leading baselines. Moreover, the model significantly reduces false negatives, a crucial factor for timely therapeutic intervention. By addressing the limitations of unimodal and superficial prediction strategies, this framework lays the groundwork for scalable, real-world applications in continuous mental health monitoring and personalized relapse prevention. Full article

This study reviews various academic discussions utilising distinct interpretations of entrepreneurship and resilience. The inadequacies of contemporary literature are explored and avenues for subsequent studies are offered in light of these discussions. Notable shifts in literature across themes, eras, and contexts have been documented. The body of literature has been steadily expanding over time, with a significant portion of research included in this SLR published from 2010 to 2024, which was not considered in earlier SLRs. A methodical, multidisciplinary evaluation of 44 publications divided into multiple academic dialogues was conducted to lay the groundwork for critical examination of each field of study. Resilience in the modern era encompasses not only the power to bounce back from stressful situations and adjust to a changed environment but also the dynamic process to improve learning capacity and foster personal development through continuous self-improvement, the acquisition of novel experiences and a forward-leaping framework. These findings contribute to the clarification and critical analysis of the current state of entrepreneurial resilience which will have several policies implications. Full article