Safety Modeling
Safety modeling aims to understand and predict traffic safety conditions for proactive mitigation and control. I develop AI-based models and applications that understand the relationships between various contributing factors, such as traffic flow, road conditions, and driver behavior, and traffic safety. By analyzing large datasets and leveraging machine learning algorithms, these models can predict crashes and conflicts in advance. This enables proactive measures to mitigate risks and enhance traffic safety. Some challenges I aim to address include:
- Real-time data integration and analysis
- Model transferability across different contexts
- High dimensionality and spatio-temporal heterogeneity in traffic data
Relevant Publications
- Li, P., Guo, H., Bao, S. and Kusari, A., 2023. "A Probabilistic Framework for Estimating the Risk of Pedestrian-Vehicle Conflicts at Intersections". IEEE Transactions on Intelligent Transportation Systems.
- Li, P., Abdel-Aty. M, Zhang, S., 2022. "Improving Spatiotemporal Transferability of Real-Time Crash Likelihood Prediction Models Using Transfer-Learning Approaches". Transportation Research Record.
- Li, P., Abdel-Aty. M, 2022. "A Hybrid Machine Learning Model for Predicting Real-time Secondary Crash Likelihood". Accident Analysis and Prevention, 165.
- Li, P., Abdel-Aty, M. and Yuan, J., 2021. "Using bus critical driving events as surrogate safety measures for pedestrian and bicycle crashes based on GPS trajectory data". Accident Analysis & Prevention, 150.
- Li, P., Abdel-Aty, M., Cai, Q. and Yuan, C., 2020. "The application of novel connected vehicles emulated data on real-time crash potential prediction for arterials".
- Li, P., Abdel-Aty, M. and Yuan, J., 2020. "Real-time crash risk prediction on arterials based on LSTM-CNN". Accident Analysis & Prevention, 135, p.105371.