I am a PhD candidate in Civil Engineering at the University of Central Florida (UCF), working as a Research Assistant at the Smart & Safe Transportation (SST) Lab under the supervision of Dr. Mohamed Abdel-Aty. I received my Master’s and Bachelor’s degrees in Transportation Engineering from Tongji University in 2023 and 2020, respectively (download my CV here).

My research focuses on data-driven transportation safety and operation modeling, with a particular emphasis on large-scale connected vehicle (CV) trajectory data applications. Specifically, my work encompasses driving-behavior-enhanced traffic safety modeling, CV-data-based network traffic operation and prediction, and innovative crash analytic methods (see my research here).

As of 2025, I have published 18 SCI papers in leading transportation journals, including Accident Analysis & Prevention, Analytic Methods in Accident Research, Transportation Research Part C, and IEEE Transactions on Intelligent Transportation Systems, with 5 as first author and 4 as corresponding author (see these publications here).

I also serve as a reviewer for more than 10 transportation journals, including Accident Analysis & Prevention, Transportation Research Part A/C/E, Expert Systems with Applications, and major conferences such as the Transportation Research Board Annual Meeting and World Transport Convention.

⭐ Featured Publications

Intersection Crash Analysis Considering Longitudinal and Lateral Risky Driving Behavior from Connected Vehicle Data: A Spatial Machine Learning Approach

Accident Analysis & Prevention (2025)

Lei Han*, Mohamed Abdel-Aty

This study proposes a spatial-ML framework integrating longitudinal and lateral risky driving behaviors from connected vehicle data for intersection crash analysis.

Crash Frequency Risky Driving Behavior Spatial Modeling CV Data ML

Transformer-Based Modeling of Abnormal Driving Events for Freeway Crash Risk Evaluation

Transportation Research Part C: Emerging Technologies (2024)

Lei Han, Rongjie Yu*, Chenzhu Wang, Mohamed Abdel-Aty

This study proposes a Transformer-based model for freeway crash risk evaluation using abnormal driving events, achieving 84.1% accuracy and 77.7% AUC and outperforming traditional methods. It also reveals the temporal-spatial decay and collective superposition effect of abnormal driving events.

Crash Prediction Risky Driving Behavior CV Data DL