Mr. Mujeeb Abiola’s research focuses on advancing transportation safety and efficiency through data-driven methodologies and emerging technologies. His work extensively employs large-scale traffic and crash data, including millions of federal highway administration records, to investigate the spatiotemporal dynamics of pedestrian crashes and the evolution of crash hotspots. Utilizing advanced statistical and machine learning models, he has developed predictive frameworks that outperform traditional Highway Safety Manual standards, providing robust insights into risk factors and injury severity in both human-driven and autonomous vehicle contexts. His research on connected and autonomous vehicles (CAVs) has led to the development of traffic control algorithms that significantly enhance safety, operational efficiency, and environmental sustainability in freeway work zones. Furthermore, his studies integrate GPU-accelerated data processing, simulation-based optimization, and multi-level heterogeneity modeling to evaluate vulnerable road user behavior and assess dynamic collision risks. Through simulation platforms such as VISSIM and SUMO, combined with Python-based data analysis and GIS applications, his work systematically addresses complex traffic scenarios, including merging, diverging, and weaving segments, while also accounting for seasonal variations and temporal constraints in crash determinants. His contributions include empirical analyses of autonomous vehicle incidents, methodological advancements in microsimulation accuracy, and development of actionable strategies for real-world traffic management, ultimately aiming to improve roadway safety, inform policy, and guide evidence-based planning in modern transportation systems.