Understanding the determinants of crash injury severity is essential for developing effective safety strategies and reducing traffic-related losses. This study proposes a hybrid analytical framework that integrates interpretable machine learning with statistical modeling to address the limitations of existing approaches. A Random Forest (RF) classifier, combined with Shapley Additive Explanations (SHAP), was first employed to capture nonlinear relationships and identify key predictors of injury outcomes, including safety equipment, age, gender, and the presence of fixed obstacles. Random Forest was chosen for its strong predictive performance in capturing nonlinear relationships, while SHAP provides transparent explanations of model predictions. To ensure statistical rigor and quantify associations, a Partial Proportional Odds (PPO) model was subsequently applied, allowing for the relaxation of the proportional odds assumption (POA) and enabling the estimation of marginal effects. The results consistently highlight the protective role of safety equipment and the increased risks associated with fixed obstacles, adverse weather, and nighttime conditions. For instance, seatbelt use is associated with a 29.61% higher probability of no injury, whereas fixed obstacles are associated with a 29.36% lower probability and a higher risk of severe injury. These findings support safety campaigns that encourage protective equipment use and infrastructure policies aimed at reducing roadside obstacles and improving nighttime visibility. Future research will focus on accounting unobserved heterogeneity and validating the framework across multi-regional datasets to improve its generalizability and policy relevance.

This review examines data-driven road traffic safety modeling, aiming to provide a comprehensive overview of the state-of-the-art and persistent research gaps. The study is structured around data sources, influencing factors, reactive and proactive modeling approaches, and key challenges. Data sources, including crashes, trajectories, traffic, roadway geometry, and environmental data, are first reviewed in the context of reactive and proactive safety analysis. To address the substantial heterogeneity across studies, a vote-counting strategy is adopted to aggregate directional evidence reported in the literature. The synthesis indicates that traffic demand variables exhibit consistently positive associations with crash occurrence, while speed-related effects are strongly context-dependent. Road geometry and surface conditions have largely consistent directional impacts on safety outcomes. From a methodological perspective, reactive approaches remain dominant, while proactive approaches exhibit potential for early risk identification but remain insufficiently validated due to data quality constraints. In addition, empirical evidence on conflict–crash relationships is still limited. Notably, model performance varies substantially across safety tasks, with algorithm effectiveness primarily driven by data structure, outcome definition, and aggregation level, rather than by the intrinsic superiority of any single approach. Overall, this review highlights challenges related to data integration, spatio-temporal modeling, interpretability, and transferability, and provides practical guidance for model selection in operational road safety analysis.

Intelligent Transportation Systems (ITS) play a central role in the development of more efficient, adaptive, and resilient road networks. Traffic control strategies have progressively evolved from traditional approaches toward more intelligent and adaptive frameworks. This paper presents a taxonomy-based perspective on intelligent traffic control strategies for road networks, organizing existing approaches according to three complementary dimensions: control scope, decision-making mechanism, and control architecture. Based on this framework, the paper discusses representative methodologies, including rule-based control, model-based methods, simulation-based optimization, data-driven and artificial intelligence-based methods, and emerging cooperative strategies enabled by connected and automated vehicles (CAVs). The analysis also examines key application domains, such as traffic signal control, ramp metering, CAV-based traffic management, and simulation platforms, highlighting their operational principles, advantages, limitations, and implementation challenges. Particular attention is given to the transition from local and reactive control toward coordinated, predictive, and learning-based traffic management systems. The paper identifies major challenges related to scalability, robustness, interpretability, safety, real-world deployment, and the gap between simulation performance and practical implementation. The proposed taxonomy also supports practical comparison and preliminary selection of context-specific strategies. Future directions point toward integrated and hybrid frameworks combining data-driven adaptability, vehicle–infrastructure cooperation, and digital twin technologies.

Predicting student dropout and academic success is important for higher education institutions for enhancing retention and deliver timely interventions. However, educational datasets often exhibit severe class imbalance, particularly when multiple academic outcomes (i.e., dropout, enrolled, and graduate) are considered simultaneously. Thus this study examines the effectiveness of three widely used over-sampling techniques (i.e., RandomOverSampler, synthetic minority oversampling technique, and adaptive synthetic sampling) for mitigating class imbalance and enhancing prediction performance. These sampling strategies are evaluated in combination with several machine learning classifiers to assess their influence on accuracy of minority-class detection. The experimental results show that appropriate over-sampling substantially improves model performance, especially for the minority categories. The findings highlight the critical role of imbalance-handling techniques in educational data mining and offer practical insights for institutions seeking to build robust early-warning systems.

Unmanned aerial vehicles (UAVs) are increasingly considered as enabling technologies for last-mile delivery, emergency medical response, and smart-city applications. However, drone-based logistics, emergency communication, sensing activities, and future aerial mobility are often addressed as separate research domains. This article proposes a four-dimensional planning framework for drone-enabled mobility, integrating goods, information, sensing, and human mobility within a unified conceptual structure. The framework is developed through a literature-informed conceptual analysis and previous applied research experiences related to drone-assisted logistics and emergency communication. Goods mobility includes parcel delivery, medical logistics, emergency supply transport, and hybrid operational models involving trucks, public transport, depots, and micro-hubs. Information mobility refers to the use of drones as mobile communication tools for emergency warnings, citizen interaction, drone-to-infrastructure communication, and infomobility services. Sensing mobility concerns traffic monitoring, environmental observation, disaster mapping, crowd monitoring, and infrastructure inspection. Human mobility is considered as an emerging extension related to urban air mobility (UAM), electric vertical take-off and landing (eVTOL) systems, and low-altitude aerial corridors. Cross-cutting issues such as energy autonomy, solar-assisted drones, multimodal integration, safety, communication, regulation, sustainability, and public acceptance are discussed. The proposed framework provides a structured basis for assessing drones as components of sustainable, resilient, and multimodal mobility systems.