Search Results (1,055)

Student dropout remains a critical challenge in higher education, especially within public universities that serve diverse and vulnerable populations. This research presents the design and evaluation of an early warning system based on an XGBoost classifier, trained exclusively on data collected at the time of student enrollment. Using a retrospective dataset of nearly 40,000 first-year students (2014–2024) from a Mexican public university, the model incorporated academic, socioeconomic, demographic, and perceptual variables. The final XGBoost model achieved an AUC-ROC of 0.6902 and an F1-score of 0.6946 for the dropout class, with a sensitivity of 88%. XGBoost was chosen over Random Forest due to its superior ability to detect students at risk, a critical requirement for early intervention. The model flagged 59% of incoming students as high-risk, with considerable variability across academic programs. The most influential predictors included age, high school GPA, conditioned admission, and other family responsibilities and economic constraints. This research demonstrates that early warning systems can transform enrollment data into timely and actionable insights, enabling universities to identify vulnerable students earlier and respond more effectively, allocate support more efficiently, and enhance their efforts to reduce dropout rates and improve student retention. Full article

Student behavior analysis plays a critical role in enhancing educational quality and enabling personalized learning. While previous studies have utilized machine learning models to analyze campus card consumption data, few have integrated multi-source behavioral data with large language models (LLMs) to provide deeper insights. This study proposes an intelligent educational system that examines the relationship between student consumption behavior and academic performance. The system is built upon a dataset collected from students of three majors at Xinjiang Normal University, containing exam scores and campus card transaction records. We designed an artificial intelligence (AI) agent that incorporates LLMs, SageGNN-based graph embeddings, and time-series regularity analysis to generate individualized behavior reports. Experimental evaluations demonstrate that the system effectively captures both temporal consumption patterns and academic fluctuations, offering interpretable and accurate outputs. Compared to baseline LLMs, our model achieves lower perplexity while maintaining high report consistency. The system supports early identification of potential learning risks and enables data-driven decision-making for educational interventions. Furthermore, the constructed multi-source dataset serves as a valuable resource for advancing research in educational data mining, behavioral analytics, and intelligent tutoring systems. Full article

In this study, bone detection was performed using the YOLO algorithm on a dataset comprising photographs of the scapula, humerus, and femur from cattle, horses, and dogs. Subsequently, convolutional neural networks (CNNs) were employed to classify both the bone type and the species. Trained on a total of 26,148 images, the model achieved an accuracy rate of up to 97.6%. The system was designed to operate not only on mobile devices but also in an offline, “closed model” version, thereby enhancing its applicability in forensic medicine settings where data security is critical. Additionally, the application was structured as a virtual assistant capable of responding to users in both written and spoken formats and of generating output in PDF format. In this regard, this study presents a significant example of digital transformation in fields such as veterinary anatomy education, forensic medicine, archaeology, and crime scene investigation, providing a solid foundation for future applications. Full article

This study presents an extended dataset on educational quality covering 101 countries, from 1970 to 2023. While existing international assessments, such as the Programme for International Student Assessment (PISA) and Trends in International Mathematics and Science Study (TIMSS), offer valuable snapshots of student performance, their limited coverage across countries and years constrains broader analyses. To address this limitation, we harmonized observed test scores across assessments and imputed missing values using both linear interpolation and machine learning (Least Absolute Shrinkage and Selection Operator (LASSO) regression). The dataset included (i) harmonized test scores for 15 year olds, (ii) annual educational quality indicators for the 15–19 age group, and (iii) educational quality indexes for the working-age population (15–64). These measures are provided in machine-readable formats and support empirical research on human capital, economic development, and global education inequalities across economies. Full article

The increasing demand for accessible and efficient machine learning solutions has led to the development of the Adaptive Learning Framework (ALF) for multi-class, single-label image classification. Unlike existing low-code tools, ALF integrates multiple transfer learning backbones with a guided, adaptive workflow that empowers non-technical users to create custom classification models without specialized expertise. It employs pre-trained models from TensorFlow Hub to significantly reduce computational costs and training times while maintaining high accuracy. The platform’s User Interface (UI), built using Streamlit, enables intuitive operations, such as dataset upload, class definition, and model training, without coding requirements. This research focuses on small-scale image datasets to demonstrate ALF’s accessibility and ease of use. Evaluation metrics highlight the superior performance of transfer learning approaches, with the InceptionV2 model architecture achieving the highest accuracy. By bridging the gap between complex deep learning methods and real-world usability, ALF addresses practical needs across fields like education and industry. Full article

Traditional educational assessment systems suffer from inefficient question selection strategies that fail to optimally probe student knowledge while requiring extensive testing time. We present a novel hierarchical probabilistic neural framework that integrates Bayesian inference with symmetric deep neural architectures to enable adaptive, efficient knowledge assessment. Our method models student knowledge as latent representations within a graph-structured concept dependency network, where probabilistic mastery states, updated through variational inference, are encoded by symmetric graph properties and symmetric concept representations that preserve structural equivalences across similar knowledge configurations. The system employs a symmetric dual-network architecture: a concept embedding network that learns scale-invariant hierarchical knowledge representations from assessment data and a question selection network that optimizes symmetric information gain through deep reinforcement learning with symmetric reward structures. We introduce a novel uncertainty-aware objective function that leverages symmetric uncertainty measures to balance exploration of uncertain knowledge regions with exploitation of informative question patterns. The hierarchical structure captures both fine-grained concept mastery and broader domain understanding through multi-scale graph convolutions that preserve local graph symmetries and global structural invariances. Our symmetric information-theoretic method ensures balanced assessment strategies that maintain diagnostic equivalence across isomorphic concept subgraphs. Experimental validation on large-scale educational datasets demonstrates that our method achieves 76.3% diagnostic accuracy while reducing the question count by 35.1% compared to traditional assessments. The learned concept embeddings reveal interpretable knowledge structures with symmetric dependency patterns that align with pedagogical theory. Our work generalizes across domains and student populations through symmetric transfer learning mechanisms, providing a principled framework for intelligent tutoring systems and adaptive testing platforms. The integration of probabilistic reasoning with symmetric neural pattern recognition offers a robust solution to the fundamental trade-off between assessment efficiency and diagnostic precision in educational technology. Full article

The proper use of Android app permissions is crucial to the success and security of these apps. Users must agree to permission requests when installing or running their apps. Despite official Android platform documentation on proper permission usage, there are still many cases of permission abuse. This study provides a comprehensive analysis of the Android permission landscape, highlighting trends and patterns in permission requests across various applications from the Google Play Store. By distinguishing between benign and malicious applications, we uncover developers’ evolving strategies, with malicious apps increasingly requesting fewer permissions to evade detection, while benign apps request more to enhance functionality. In addition to examining permission trends across years and app features such as advertisements, in-app purchases, content ratings, and app sizes, we leverage association rule mining using the FP-Growth algorithm. This allows us to uncover frequent permission combinations across the entire dataset, specific years, and 16 app genres. The analysis reveals significant differences in permission usage patterns, providing a deeper understanding of co-occurring permissions and their implications for user privacy and app functionality. By categorizing permissions into high-level semantic groups and examining their application across distinct app categories, this study offers a structured approach to analyzing the dynamics within the Android ecosystem. The findings emphasize the importance of continuous monitoring, user education, and regulatory oversight to address permission misuse effectively. Full article

This study investigates the drivers of individual and joint adoption of sustainable land use (SLU) practices—specifically crop choice and soil and water conservation—and their impact on farm performance (crop revenue) and production risk (crop yield skewness). Using a farm-level dataset of 504 households across three agro-ecological zones in Punjab, Pakistan, we address selectivity bias through the newly developed multinomial endogenous switching regression (MESR) model. Additionally, we assess land use sustainability across ecological, social, and economic dimensions using a comprehensive non-parametric approach. Our findings identify key determinants of SLU adoption, including farmer education, access to advisory services, FBO membership, hired labor, climate information, farm size, and perceptions of drought and heatwaves. We demonstrate that joint adoption of SLU practices maximizes crop revenue and reduces production risk, lowering the likelihood of crop failure. The study further suggests complementarity between these SLU practices in enhancing crop revenue. Moreover, joint adopters of SLU practices significantly outperform non-adopters in ecological, social, and economic sustainability dimensions. We recommend improving access to public sector farm advisory services and climate information to enable farmers to make well-informed decisions based on reliable data. Implementing these measures can support the transition toward sustainable land management, helping to mitigate risks like crop failure and declining revenues, which threaten farm income. Full article

Introduction: Dental caries remains a public health concern, and early detection prevents its progression and complications. Panoramic radiographs are essential diagnostic tools, yet the interpretation of panoramic X-rays varies among practitioners. Artificial intelligence (AI) presents a promising approach to enhance diagnostic accuracy in detecting dental caries. This scoping review examines the current literature on the use of AI programs to analyze panoramic radiographs for the diagnosis of dental caries. Methods: This scoping review searched PubMed, Scopus, Web of Science, and Dentistry and Oral Sciences Source, adhering to PRISMA guidelines. The review included peer-reviewed, original research published in English that investigated the use of AI to diagnose dental caries. Data were extracted on the AI model characteristics, advantages, disadvantages, and diagnostic performance. Results: Seven studies met the inclusion criteria. The Deep Learning Model achieved the highest performance (specificity 0.9487, accuracy 0.9789, F1 score 0.9245), followed by Diagnocat and Tooth Type Enhanced Transformer. Models such as CranioCatch and CariSeg showed moderate performance, while the Dental Caries Detection Network demonstrated the lowest. Benefits included improved diagnostic support and workflow efficiency, while limitations involved dataset biases, interpretability challenges, and computational demands. Conclusions: Applying AI technologies to panoramic X-rays demonstrates the potential for enhancing caries diagnosis, with some models achieving near-expert performance. However, future research must address the generalizability, transparency, and integration of AI models into clinical practice. Future research should focus on diverse training datasets, explainable AI development, clinical validation, and incorporating AI training into dental education and training. Full article

The degradation of physical student examination archives, particularly handwritten essay booklets, presents a significant barrier to longitudinal academic research, institutional record preservation, and student performance analysis. This study introduces a novel natural language processing (NLP)-based framework for the automated reconstruction of damaged academic essay manuscripts using a span-infilling transformer architecture. A synthetic dataset comprising 5000 paired samples of damaged Text and full Text was curated from archived Data Science examination scripts collected at the Center for Applied Data Science, Sol Plaatje University, South Africa. The proposed method fine-tunes a T5-based encoder–decoder model, leveraging span corruption and task-specific prompting to restore missing or illegible segments. Comprehensive evaluation using ROUGE-L, BLEU-4, and BERTScore demonstrates substantial improvements over baseline models including BERT and GPT-2. Qualitative assessments by academic experts further validate the fluency, coherence, and contextual relevance of restored texts. Training dynamics reveal stable convergence without overfitting, while ablation studies confirm the contribution of each architectural component. Token-level error analyses and confidence-scored predictions provide additional interpretability. The proposed framework offers a scalable and effective solution for educational institutions seeking to digitize and recover lost historical student essay records, with potential extensions to other domains, such as digital humanities and archival restoration. Full article

Predicting undergraduate student success is critical for informing timely interventions and improving outcomes in higher education. This study leverages over a decade of historical data from Louisiana State University (LSU) to forecast graduation outcomes using advanced machine learning techniques, with a focus on convolutional autoencoders (CAEs). We detail the data processing and transformation steps, including feature selection and imputation, to construct a robust dataset. The CAE effectively extracts meaningful latent features, validated through low-dimensional t-SNE visualizations that reveal clear clusters based on class labels, differentiating students likely to graduate from those at risk. A two-year gap strategy is introduced to ensure rigorous evaluation and simulate real-world conditions by predicting outcomes on unseen future data. Our results demonstrate the promise of CAE-derived embeddings for dimensionality reduction and computational efficiency, with competitive performance in downstream classification tasks. While models trained on embeddings showed slightly reduced performance compared to raw input data, with accuracies of 83% and 85%, respectively, their compactness and computational efficiency highlight their potential for large-scale analyses. The study emphasizes the importance of rigorous preprocessing, feature engineering, and evaluation protocols. By combining these approaches, we provide actionable insights and adaptive modeling strategies to support robust and generalizable predictive systems, enabling educators and administrators to enhance student success initiatives in dynamic educational environments. Full article

Background: China is confronted with the dual challenges of deeply interwoven population aging and the digitalization process. The digital integration and mental health issues of the elderly group are becoming increasingly prominent. Objectives: The present study aimed to analyze the pathways through which individual, family, and social factors influence Internet use in the elderly through a multi-level analysis framework, to examine the association between Internet use and mental health with a view to providing empirical evidence for digital technology-based mental health intervention programs for the elderly, and to promote the scientific practice of the goal of healthy aging. Methods: Based on the data of the 2021 China General Social Survey (CGSS) and provincial Internet development indicators, a mixed cross-sectional dataset was constructed. Logistic hierarchical regression and OLS regression methods were adopted to systematically investigate the multi-level factors associated with Internet use among the elderly group and its association with mental health. Results: The results indicate that individual resources (younger age, higher education level, and good health status) and family technical support (family members’ Internet access) are strongly associated with Internet usage among the elderly, while regional Internet penetration rate appears to operate indirectly through micro-mechanisms. Analysis of the association with mental health showed that Internet use was related to a lower score of depressive tendency (p < 0.05), and this association remained robust after controlling for variables at the individual, family, and social levels. Conclusions: The research results provide empirical evidence for the health promotion policies for the elderly, advocating the construction of a collaborative intervention framework of “individual ability improvement–intergenerational family support–social adaptation for the elderly” to bridge the digital divide and promote the digital integration of the elderly population in China. Full article

The increasing cultural and demographic diversity among higher education students highlights the challenges regarding accessibility and inclusion. The COVID-19 pandemic has accelerated the shift toward flexible, technology-based teaching practices. However, inclusive, and accessible pedagogical practices lack consistency, particularly when supporting students with disabilities or diverse learning needs. This study evaluates the effectiveness of the Learning Design for Flexible Education (FLeD) Tool—a web-based platform developed to support teachers in designing flexible and inclusive learning scenarios. The research adopts a qualitative approach, featuring semi-structured interviews with two Portuguese experts in accessibility and inclusion. The experts analyzed three learning scenarios designed using the FLeD Tool, through the lens of Universal Design for Learning standards. The collected dataset was analyzed using thematic analysis to identify common issues, strengths, and opportunities for improvement. The findings show a gap between institutional policies and their practical application, mainly due to inconsistent teacher training and technical limitations. While the FLeD Tool supports more flexible and inclusive pedagogical designs, experts have identified key shortcomings such as the lack of automated accessibility checks and limited support for specific disabilities. Despite the reduced number of participants (two experts) and dataset (three learning scenarios), which limits the study’s generalizability, the conclusions draw attention to the pivotal role of systematic teacher training, embedded accessibility features and solid institutional policies in bridging the gap between policy aspiration and effective inclusive practice. 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

This research advances the integration of terrestrial laser scanning (TLS) in heritage documentation, targeting the development of holistic and practical guidance for practitioners to adopt the technology effectively. Acknowledging the pivotal role of TLS in capturing detailed and accurate representations of cultural heritage, the study emerges against a backdrop of technological progression and the evolving needs of heritage conservation. Through a comprehensive literature review, critical case studies of heritage sites in the U.S., expert interviews, and the development of a TLS for Heritage Documentation Best Practice Guide (the guide), the paper addresses the existing gaps in streamlined practices in the domain of TLS’s applications in heritage documentation. While recognizing and building upon foundational efforts such as international guidelines developed over the past decades, this study contributes a practice-oriented perspective grounded in field experience and case-based analysis. The developed guide seeks to equip practitioners with structured methods and practical tools to optimize the use of TLS, ultimately enhancing the quality and accessibility of heritage documentation. It also sets a foundation for integrating TLS datasets with other technologies, such as Building Information Modeling (BIM), virtual reality (VR), and augmented reality (AR) for heritage preservation, tourism, education, and interpretation, ultimately enhancing access to and engagement with cultural heritage sites. The paper also critically situates this guidance within the evolving theoretical discourse on digital heritage practices, highlighting its alignment with and divergence from existing methodologies. Full article