Abstract The rapid expansion of digital learning ecosystems and online educational platforms has generated substantial educational interaction data that can be utilized for intelligent forecasting and educational decision making. The COVID-19 pandemic further accelerated global dependence on online learning systems, thereby increasing the need for predictive analytical frameworks capable of understanding temporal educational behavior evolution. This study presents a machine learning based forecasting framework for... The rapid expansion of digital learning ecosystems and online educational platforms has generated substantial educational interaction data that can be utilized for intelligent forecasting and educational decision making. The COVID-19 pandemic further accelerated global dependence on online learning systems, thereby increasing the need for predictive analytical frameworks capable of understanding temporal educational behavior evolution. This study presents a machine learning based forecasting framework for predicting online learning activity trends using the dataset, “A.....Covid-19”. Dataset on Online Learning based Web Behavior from Different Countries Before and After COVID-19. The proposed framework integrates Random Forest Regression, Extreme Gradient Boosting (XGBoost), and Support Vector Regression (SVR) for both single-country and simultaneous multi country forecasting. Comparative benchmarking was conducted using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results demonstrate that XGBoost achieved superior forecasting performance because of its gradient-boosting optimization capability and nonlinear feature-learning efficiency. The developed framework further demonstrates the feasibility of AI-driven educational forecasting for large scale educational trend monitoring, digital infrastructure planning, and intelligent online learning analytics. The study also identifies several research directions involving explainable AI, deep learning forecasting architectures, and ethical educational intelligence systems. Read More Read Less

Abstract Industrial Internet of Things (IIoT) systems underpin modern smart manufacturing, yet their heterogeneous, interconnected architectures pose significant challenges for regression testing and software validation. This study proposes a requirement-aware intelligent regression test prioritization framework designed to enhance fault detection efficiency and testing scalability in IIoT environments. The framework integrates requirement traceability analysis, multi-factor prioritization scoring, and optimization-driven test selection to dynamically order regression test cases... Industrial Internet of Things (IIoT) systems underpin modern smart manufacturing, yet their heterogeneous, interconnected architectures pose significant challenges for regression testing and software validation. This study proposes a requirement-aware intelligent regression test prioritization framework designed to enhance fault detection efficiency and testing scalability in IIoT environments. The framework integrates requirement traceability analysis, multi-factor prioritization scoring, and optimization-driven test selection to dynamically order regression test cases based on fault detection capability, execution time, requirement criticality, and interface complexity. Empirical evaluation using a GSM2017 Mobile IoT dataset comprising 51 requirements and 41 test cases demonstrates that the proposed Dynamic Prioritization strategy achieves superior performance across multiple metrics: Average Percentage of Fault Detection (APFD) of 0.92, runtime reduction of 44.14%, fault coverage of 96%, and requirement coverage retention of 98.04%. Statistical validation via Wilcoxon Signed-Rank and Friedman tests confirms the significance of observed improvements. Convergence analysis indicates that Genetic Algorithm and Simulated Annealing metaheuristics effectively balance exploration and exploitation in large-scale test suite optimization. Feature importance analysis reveals fault detection capability as the dominant prioritization factor, while Pareto optimization demonstrates achievable trade-offs between execution efficiency and verification completeness. Machine learning classification using XGBoost and Neural Networks further validates the framework’s capacity for autonomous, AI-driven test prioritization. Collectively, these findings establish a robust, scalable methodology for intelligent IIoT regression testing that supports requirement traceability, adaptive prioritization, and statistically verified performance gains, advancing the state of software validation in Industry 4.0 ecosystems. Read More Read Less

Abstract Digital transformation has become a fundamental requirement for socioeconomic development, governance modernization, and inclusive service delivery across nations. However, substantial disparities remain in digital inclusion, infrastructure maturity, data accessibility, and the effectiveness of identity systems between developed and developing economies. This paper presents a unified, journal-ready predictive artificial intelligence (AI) framework that integrates machine learning, deep learning, explainable AI, federated learning, and multi-criteria decision analysis... Digital transformation has become a fundamental requirement for socioeconomic development, governance modernization, and inclusive service delivery across nations. However, substantial disparities remain in digital inclusion, infrastructure maturity, data accessibility, and the effectiveness of identity systems between developed and developing economies. This paper presents a unified, journal-ready predictive artificial intelligence (AI) framework that integrates machine learning, deep learning, explainable AI, federated learning, and multi-criteria decision analysis (MCDA) techniques to enable a comprehensive assessment of digital transformation. The proposed framework consolidates ten interconnected predictive architectures into a coherent analytical pipeline that forecasts digital inclusion trends, infrastructure readiness, accessibility inequalities, and the effectiveness of national digital identity. The study utilizes cross-country panel data spanning multiple years and integrates predictive modeling techniques such as Random Forest, XGBoost, CatBoost, Long Short-Term Memory (LSTM) networks, Temporal Fusion Transformers, Graph Neural Networks, and federated optimization methods. In addition, the framework incorporates AHP-TOPSIS-VIKOR decision mechanisms for global digital readiness ranking and explainable AI modules using SHAP and LIME for transparent policy interpretation. The proposed system enables country-level forecasting, inequality detection, infrastructure maturity classification, governance optimization, and long-term strategic policy simulation. The paper further discusses statistical analyses, visualization strategies, geospatial mapping, and dashboard architectures that can be generated from the framework. The integrated methodologyprovides a scalable and interpretable foundation for AI-assisted smart governance, sustainable digital transformation, and evidence-based digital policy planning. Read More Read Less