Search Results (3,784)

A principal factor of the fourth Industrial Revolution is the Internet of Things (IoT), a network of “smart” objects that communicate by exchanging helpful information about themselves and their environment. Our research aims to address the gaps in the existing literature regarding the educational and technological affordances of IoT applications in learning environments in secondary education. Our systematic review using the PRISMA method allowed us to extract 25 empirical studies from the last 10 years. We present the categorization of educational and technological affordances, as well as the devices used in these environments. Moreover, our findings indicate widespread adoption of organized educational activities and design-based learning, often incorporating tangible interfaces, smart objects, and IoT applications, which enhance student engagement and interaction. Additionally, we identify the impact of IoT-based learning on knowledge building, autonomous learning, student attitude, and motivation. The results suggest that the IoT can facilitate personalized and experiential learning, fostering a more immersive and adaptive educational experience. Based on these findings, we discuss key recommendations for educators, policymakers, and researchers, while also addressing this study’s limitations and potential directions for future research. Full article

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

Pediatric asthma is a multifactorial and heterogeneous disease determined by the dynamic interplay of genetic susceptibility, environmental exposures, and immune dysregulation. Recent advances have highlighted the pivotal role of epigenetic mechanisms, in particular, DNA methylation, histone modifications, and non-coding RNAs, in the regulation of inflammatory pathways contributing to asthma phenotypes and endotypes. This review examines the role of respiratory viruses such as respiratory syncytial virus (RSV), rhinovirus (RV), and other bacterial and fungal infections that are mediators of infection-induced epithelial inflammation that drive epithelial homeostatic imbalance and induce persistent epigenetic alterations. These alterations lead to immune dysregulation, remodeling of the airways, and resistance to corticosteroids. A focused analysis of T2-high and T2-low asthma endotypes highlights unique epigenetic landscapes directing cytokines and cellular recruitment and thereby supports phenotype-specific aspects of disease pathogenesis. Additionally, this review also considers the role of miRNAs in the control of post-transcriptional networks that are pivotal in asthma exacerbation and the severity of the disease. We discuss novel and emerging epigenetic therapies, such as DNA methyltransferase inhibitors, histone deacetylase inhibitors, miRNA-based treatments, and immunomodulatory probiotics, that are in preclinical or early clinical development and may support precision medicine in asthma. Collectively, the current findings highlight the translational relevance of including pathogen-related biomarkers and epigenomic data for stratifying pediatric asthma patients and for the personalization of therapeutic regimens. Epigenetic dysregulation has emerged as a novel and potentially transformative approach for mitigating chronic inflammation and long-term morbidity in children with asthma. Full article

The Internet of Medical Things (IoMT) is revolutionizing healthcare by enabling continuous patient monitoring, early diagnosis, and personalized treatments. However, the het-erogeneity of IoMT devices and the lack of standardized protocols introduce serious security vulnerabilities. To address these challenges, we propose a hybrid BiLSTM-DNN intrusion detection system, named HBiLD-IDS, that combines Bidirectional Long Short-Term Memory (BiLSTM) networks with Deep Neural Networks (DNNs), leveraging both temporal dependencies in network traffic and hierarchical feature extraction. The model is trained and evaluated on the CICIoMT2024 dataset, which accurately reflects the diversity of devices and attack vectors encountered in connected healthcare environments. The dataset undergoes rigorous preprocessing, including data cleaning, feature selection through correlation analysis and recursive elimination, and feature normalization. Compared to existing IDS models, our approach significantly enhances detection accuracy and generalization capacity in the face of complex and evolving attack patterns. Experimental results show that the proposed IDS model achieves a classification accuracy of 98.81% across 19 attack types confirming its robustness and scalability. This approach represents a promising solution for strengthening the security posture of IoMT networks against emerging cyber threats. Full article

This article addresses the task of building personalized educational recommendations based on a heterogeneous knowledge graph that integrates data from university curricula, job vacancies, and online courses. To solve the problem of course recommendations by their relevance to a user’s competencies, a graph neural network (GNN)-based approach is proposed, specifically utilizing and comparing the Heterogeneous Graph Transformer (HGT) architecture, Graph Sample and Aggregate network (GraphSAGE), and Heterogeneous Graph Attention Network (HAN). Experiments were conducted on a heterogeneous graph comprising various node and relation types. The models were evaluated using regression and ranking metrics. The results demonstrated the superiority of the HGT-based recommendation model as a link regression task, especially in terms of ranking metrics, confirming its suitability for generating accurate and interpretable recommendations in educational systems. The proposed approach can be useful for developing adaptive learning recommendations aligned with users’ career goals. Full article

Background Sex disparity has been highlighted in personalized medicine for various human diseases including acute/chronic liver diseases. In the transplant community, greater graft failure risk in female-to-male liver transplantation (LT) has been repeatedly reported, and a recent study in living donor LT reported that the inferiority of female-to-male LT is shown only when donor age is ≤40 y. We aimed to analyze the United Network for Organ Sharing (UNOS) database to test if the poorer outcome of female-to-male LT changes by donor age of 40 y in deceased donor LT, as shown in living donor LT. Methods In this retrospective cohort study, 11,752 adult patients in the UNOS registry who underwent deceased donor LT between 2000–2023 were analyzed. Multivariable analysis was performed to adjust the effects from transplant years, graft ischemia time, disease severity, and others. The primary outcome was graft failure. Results Within the subgroup of recipients with ≤40 y donors, graft failure risk was significantly greater in female-to-male LT than others (vs. female-to-female, HR = 1.43 [1.16–1.76], p < 0.001; vs. male-to-female, HR = 1.46 [1.18–1.81], p < 0.001; vs. male-to-male, HR = 1.26 [1.16–1.49], p = 0.009). In contrast, within the subgroup of recipients with >40 y donors, the risk was comparable between female-to-male LT and other donor-recipient sex groups (vs. female-to-female, p = 0.907; vs. male-to-female, p = 0.781; vs. male-to-male, p = 0.937). We tested various cutoff donor ages and determined that 40 y is the best cutoff value to define the risk subgroup in female-to-male LT. Conclusions In the current study, we found that the sex disparity shown in living donor LT is also observed in deceased donor LT. That is, post-transplant graft failure risk was greater in female-to-male LT than other donor–recipient sex groups only when donor age was ≤40 y. In contrast, graft failure risk was comparable irrespective of donor-recipient sex combinations when donor age was >40 y. Full article

Personal Rapid Transit (PRT) and Group Rapid Transit (GRT) are classes of fully automated public transport systems, where passengers can travel in small vehicles on an interconnected, grade-separated network of guideways, non-stop, from origin to destination. PRT and GRT are considered sustainable as they are low-emission and able to attract car drivers. The parameterized cost modeling framework developed in this paper has the advantage that profitability of different PRT/GRT systems can be rapidly verified in a transparent way and in function of a variety of relevant system parameters. This framework may contribute to a more transparent, rapid, and low-cost evaluation of PRT/GRT schemes for planning and decision-making purposes. The main innovation is the introduction of the “peak hour network saturation” S: the number of vehicles in circulation during peak hour divided by the maximum number of vehicles running at line speed with minimum time headways. It is an index that aggregates the main uncertainties in the planning process, namely the demand level relative to the supply level. Furthermore, a maximum S can be estimated for a PRT/GRT project, even without a detailed demand estimation. The profit per trip is analytically derived based on S and a series of more certain parameters, such as fares, capital and maintenance costs, daily demand curve, empty vehicle share, and physical properties of the system. To demonstrate the ability of the framework to analyze profitability in function of various parameters, we apply the methods to a single vehicle PRT, a platooned PRT, and a mixed PRT/GRT. The results show that PRT services with trip length proportional fares could be profitable already for $S>0.25$. The PRT capacity, profitability, and robustness to tripled infrastructure costs can be increased by vehicle platooning or GRT service during peak hours. Full article

Privacy preservation poses significant challenges in third-party data sharing, particularly when handling table data containing personal information such as demographic and behavioral records. Synthetic table data generation has emerged as a promising solution to enable data analysis while mitigating privacy risks. While Generative Adversarial Networks (GANs) are widely used for this purpose, they exhibit limitations in modeling table data due to challenges in handling mixed data types (numerical/categorical), non-Gaussian distributions, and imbalanced variables. To address these limitations, this study proposes a novel adversarial learning framework integrating gradient boosting trees for synthesizing table data, called Adversarial Gradient Boosting Decision Tree (AGBDT). Experimental evaluations on several datasets demonstrate that our method outperforms representative baseline models regarding statistical similarity and machine learning utility. Furthermore, we introduce a privacy-aware adaptation of the framework by incorporating k-anonymization constraints, effectively reducing overfitting to source data while maintaining practical usability. The results validate the balance between data utility and privacy preservation achieved by our approach. Full article

Background: Prostate cancer (PC) is the second leading cause of cancer-related death in men in the United States. A subset of patients develops non-metastatic, castration-resistant PC (nmCRPC), for which management requires a personalized consideration for appropriate treatment. However, there is no consensus regarding when to switch from androgen deprivation therapy (ADT) to more aggressive treatments like abiraterone or enzalutamide. Methods: We analyzed 5037 nmCRPC patients and employed a Weibull Time to Event Recurrent Neural Network to identify patients who would benefit from switching from ADT to abiraterone/enzalutamide. We evaluated this model using differential treatment benefits measured by the Kaplan–Meier estimation and milestone probabilities. Results: The model achieved an area under the curve of 0.738 (standard deviation (SD): 0.057) for patients treated with abiraterone/enzalutamide and 0.693 (SD: 0.02) for patients exclusively treated with ADT at the 2-year milestone. The model recommended 14% of ADT patients switch to abiraterone/enzalutamide. Analysis showed a statistically significant absolute improvement using model-recommended treatments in progression-free survival (PFS) of 0.24 (95% confidence interval (CI): 0.23–0.24) at the 2-year milestone (PFS rate increasing from 0.50 to 0.74) with a hazard ratio of 0.44 (95% CI: 0.39–0.50). Conclusions: Our model successfully identified nmCRPC patients who would benefit from switching to abiraterone/enzalutamide, demonstrating potential outcome improvements. Full article

Mental stress is a psychological or emotional strain that typically occurs because of threatening, challenging, and overwhelming conditions and affects human behavior. Various factors, such as professional, environmental, and personal pressures, often trigger it. In recent years, various deep learning (DL)-based schemes using electroencephalograms (EEGs) have been proposed. However, the effectiveness of DL-based schemes is challenging because of the intricate DL structure, class imbalance problems, poor feature representation, low-frequency resolution problems, and complexity of multi-channel signal processing. This paper presents a novel hybrid DL framework, BDDNet, which combines a deep convolutional neural network (DCNN), bidirectional long short-term memory (BiLSTM), and deep belief network (DBN). BDDNet provides superior spectral–temporal feature depiction and better long-term dependency on the local and global features of EEGs. BDDNet accepts multiple EEG features (MEFs) that provide the spectral and time-domain features of EEGs. A novel improved crow search algorithm (ICSA) was presented for channel selection to minimize the computational complexity of multichannel stress detection. Further, the novel employee optimization algorithm (EOA) is utilized for the hyper-parameter optimization of hybrid BDDNet to enhance the training performance. The outcomes of the novel BDDNet were assessed using a public DEAP dataset. The BDDNet-ICSA offers improved recall of 97.6%, precision of 97.6%, F1-score of 97.6%, selectivity of 96.9%, negative predictive value NPV of 96.9%, and accuracy of 97.3% to traditional techniques. Full article

Schizophrenia (SZ) is a complex neuropsychiatric disorder characterized by heterogeneous symptoms, relatively poor clinical outcome, and widespread disruptions in neural connectivity and oscillatory dynamics. This article attempts to review current evidence linking genomic and proteomic alterations with aberrant neural oscillations observed in SZ, including aberrations in all oscillatory frequency bands obtained via human EEG. The numerous genes discussed are mainly involved in modulating synaptic transmission, synaptic function, interneuron excitability, and excitation/inhibition balance, thereby influencing the generation and synchronization of neural oscillations at specific frequency bands (e.g., gamma frequency band) critical for different cognitive, emotional, and perceptual processes in humans. The review highlights how polygenic influences and gene–circuit interactions underlie the neural oscillatory and connectivity abnormalities central to SZ pathophysiology, providing a framework for future research on common genetic-neural function interactions and on potential therapeutic interventions targeting local and global network-level neural dysfunction in SZ patients. As will be discussed, many of these genes affecting neural oscillations in SZ also affect other neurological disorders, ranging from autism to epilepsy. In time, it is hoped that future research will show why the same genetic anomaly leads to one illness in one person and to another illness in a different person. Full article

This study investigates how young Chinese consumers across generational lines engage with wine, addressing three key research questions: What motivates their wine purchases? What sensory preferences do they exhibit? And through which channels do they prefer to buy wine? Based on a qualitative design combining focus groups and semi-structured interviews, the study identifies significant generational differences between millennials and post-millennials. Millennials treat wine as a social tool for networking and status, while post-millennials view wine as a medium of personal identity shaped by digital culture. Similarly, millennials prefer a balance of traditional and digital retail, whereas post-millennials favour online platforms. Experiential consumption follows the same pattern, from formal tourism to virtual tastings. By linking these findings to institutional and cultural theories of consumer behaviour, the study contributes to a nuanced understanding of wine consumption in an emerging market. It provides practical implications for wine marketers aiming to localize their strategies for younger Chinese segments. Full article

Background: Transcranial direct current stimulation (tDCS) has emerged as a promising neuromodulatory tool for language rehabilitation in chronic aphasia. However, the effects of bi-hemispheric, multisite stimulation remain largely unexplored, especially in people with chronic and treatment-resistant language impairments. The goal of this study is to look at the effects on behavior and brain activity of an individualized language training program that combines bi-hemispheric multisite anodal tDCS with personalized language training for Albert, a patient with long-standing, treatment-resistant non-fluent aphasia. Methods: Albert, a right-handed retired physician, had transcortical motor aphasia (TCMA) subsequent to a left-hemispheric ischemic stroke occurring more than six years before the operation. Even after years of traditional treatment, his expressive and receptive language deficits remained severe and persistent despite multiple rounds of traditional therapy. He had 15 sessions of bi-hemispheric multisite anodal tDCS aimed at bilateral dorsal language streams, administered simultaneously with language training customized to address his particular phonological and syntactic deficiencies. Psycholinguistic evaluations were performed at baseline, immediately following the intervention, and at 1, 2, 3, and 6 months post-intervention. Resting-state fMRI was conducted at baseline and following the intervention to evaluate alterations in functional connectivity (FC). Results: We noted statistically significant enhancements in auditory sentence comprehension and oral reading, particularly at the 1- and 3-month follow-ups. Neuroimaging showed decreased functional connectivity (FC) in the left inferior frontal and precentral regions (dorsal stream) and in maladaptive right superior temporal regions, alongside increased FC in left superior temporal areas (ventral stream). This pattern suggests that language networks may be reorganizing in a more efficient way. There was no significant improvement in phonological processing, which may indicate reduced connectivity in the left inferior frontal areas. Conclusions: This case underscores the potential of combining individualized, network-targeted language training with bi-hemispheric multisite tDCS to enhance recovery in chronic, treatment-resistant aphasia. The convergence of behavioral gains and neuroplasticity highlights the importance of precision neuromodulation approaches. However, findings are preliminary and warrant further validation through controlled studies to establish broader efficacy and sustainability of outcomes. Full article

Knowledge-graph-based recommendation aims to provide personalized recommendation services to users based on their historical interaction information, which is of great significance for shopping transaction rates and other aspects. With the rapid growth of online shopping, the knowledge graph constructed from users’ historical interaction data now incorporates multiattribute information, including timestamps, images, and textual content. The information of multiple modalities is difficult to effectively utilize due to their different representation structures and spaces. The existing methods attempt to utilize the above information through simple embedding representation and aggregation, but ignore targeted representation learning for information with different attributes and learning effective weights for aggregation. In addition, existing methods are not sufficient for effectively modeling temporal information. In this article, we propose MTR, a knowledge graph recommendation framework based on mixture of experts network. To achieve this goal, we use a mixture-of-experts network to learn targeted representations and weights of different product attributes for effective modeling and utilization. In addition, we effectively model the temporal information during the user shopping process. A thorough experimental study on popular benchmarks validates that MTR can achieve competitive results. Full article

The purpose of the present research is to analyse the negative outcomes associated with the excessive Instagram dependency of those users that access the application through their smartphones. An empirical study was conducted through online interviews using structured questionnaires, resulting in 342 valid responses, with the target population being young users over 18 years old who access Instagram daily. Research shows that dependency on Instagram is primarily driven by individuals’ need for orientation and understanding, with entertainment being a secondary motivation. The results indicate that dependency on the social network is positively associated with excessive use, addiction, and Instastress. Furthermore, excessive use contributes to personal and social problems and increases both stress levels and mindfulness related to the platform. In turn, this excessive use intensifies addiction, which functions as a mediating variable between overuse and Instastress, mindfulness, and emotional exhaustion. This study offers valuable insights for academics, mental health professionals, and marketers by emphasizing the importance of fostering healthier digital habits and developing targeted interventions. Full article