Abstract This study presents a Random Forest-based machine learning framework for predicting student academic performance using behavioral engagement metrics within e-learning environments. Analyzing a dataset of 14,003 student records encompassing academic, behavioral, and demographic attributes, we evaluated three predictive... This study presents a Random Forest-based machine learning framework for predicting student academic performance using behavioral engagement metrics within e-learning environments. Analyzing a dataset of 14,003 student records encompassing academic, behavioral, and demographic attributes, we evaluated three predictive models Linear Regression, Random Forest, and Multilayer Perceptron neural networks to forecast final academic grades categorized into four ordinal levels. A critical methodological contribution of this research is the identification and mitigation of data leakage: initial experiments revealed that including ExamScore as a predictor artificially inflated performance metrics (R² = 1.000), as FinalGrade is deterministically derived from examination scores. After excluding this variable, the hyperparameter-tuned Random Forest classifier emerged as the superior model, achieving an R² score of 0.792, a classification accuracy of 84.2%, and a weighted F1-score of 0.842, significantly outperforming baseline approaches. Feature importance analysis demonstrated that behavioral engagement indicators specifically AssignmentCompletion (18.3%), Attendance (18.0%), and StudyHours (16.5%) were the most influential predictors, whereas demographic variables such as Gender (3.0%) exhibited minimal predictive power. These findings suggest that modifiable learning behaviors, rather than static demographic characteristics, drive academic outcomes. The study provides actionable insights for educational institutions to develop early intervention systems that monitor engagement metrics and deliver equitable, personalized support. Limitations include the cross-sectional design and institutional specificity, warranting future research on temporal modeling, explainable AI integration, and cross institutional validation to enhance generalizability and ethical deployment of predictive learning analytics. Read More Read Less

Abstract This study presents a data-driven assessment of global airport disruption risks, analysing 76 disruption events across 26 airports spanning five global regions: the Middle East, South Asia, Europe, the Asia Pacific, and North Africa. This study is... This study presents a data-driven assessment of global airport disruption risks, analysing 76 disruption events across 26 airports spanning five global regions: the Middle East, South Asia, Europe, the Asia Pacific, and North Africa. This study is based on empirical data on airport disruptions collected during the 2026 USIran war. A novel Disruption Impact Index (DII) is introduced to quantify operational consequences by integrating three core variables: severity level (scored 1–5), disruption duration (in hours), and the number of flights affected. Airport-level risk scores are computed by aggregating DII values across all recorded events at each location. The methodology employs descriptive statistics, correlation analysis, Principal Component Analysis (PCA), and K-means clustering (with optimal k=4 determined via Elbow Method and validated by Silhouette Score) to identify structural patterns in disruption vulnerability. Results reveal that Middle Eastern airports account for approximately 80% of total disruption risk, with Abu Dhabi (AUH), Kuwait (KWI), and Baghdad (BGW) ranking highest. The number of affected flights shows the strongest correlation with disruption impact (r = 0.86), followed by severity level (r = 0.72) and duration (r = 0.69). Four distinct airport clusters were identified, ranging from high risk Gulf hubs vulnerable to fuel shortages and security issues to lower-risk regional airports experiencing operational delays. PCA confirmed that the first two principal components explain 78–82% of total variance, validating the multidimensional nature of disruption risk. These findings support evidence-based decision making for strengthening network wide resilience, recommending priority monitoring for critical airports, fuel reserve protocols for Gulf regions, and strategic utilization of lower risk airports as diversion hubs during regional crises. Read More Read Less

Abstract Smart IoT technologies have emerged as transformative innovations for advancing sustainability through real-time monitoring and control of environmental systems. This structured review examines the application of IoT across urban infrastructure, water resource management, and smart buildings. The... Smart IoT technologies have emerged as transformative innovations for advancing sustainability through real-time monitoring and control of environmental systems. This structured review examines the application of IoT across urban infrastructure, water resource management, and smart buildings. The study highlights how integrated sensors, communication networks, and data analytics enhance operational efficiency in energy, waste, and water sectors. Specifically, it explores IoT-based water monitoring systems, detailing architectures for leak detection, quality assessment, and consumption management. A four-layer conceptual architecture comprising sensing, communication, data processing, and application layers is proposed to structure these systems. Despite significant advancements, the review identifies critical challenges hindering widespread deployment, including data security, scalability, interoperability, and high implementation costs. Comparative analyses of existing literature reveal gaps in multi-sensor integration and energy efficiency. The paper concludes that while IoT-driven systems offer immense potential for sustainable resource management and smart city development, realizing this potential requires overcoming technical fragmentation. Future research must focus on developing scalable, secure, and interoperable ecosystems through cross-sector collaboration. This synthesis provides a roadmap for advancing IoT-driven environmental monitoring to support sustainable urban governance. Additionally, the review emphasizes incorporating emerging technologies like artificial intelligence and blockchain to enhance system performance. By addressing current limitations in sensor integration and data management, stakeholders can optimize resource utilization. Ultimately, this paper underscores the critical role of IoT in achieving sustainable urban development through intelligent, data-driven environmental monitoring solutions. Read More Read Less