December 3rd, 2025
Nancy Huynh successfully defended her M.Sc on December 3rd, 2025!
Citywide Traffic Volume Estimations with Uncertainty: A Network Geostatistical Boosting Approach
Her thesis presents a hybrid Network Geostatistical Boosting framework that combines XGBoost regression with network-based kriging to estimate traffic volumes across Edmonton’s road network and quantify uncertainty. The method generates AAWDT estimates for 4,245 segments, provides uncertainty (kriging variance) maps, and includes an optimization model for placing future MioVision traffic counters. The framework improves predictive accuracy, supports informed decision-making, and offers a practical tool for traffic monitoring and planning.
Dr. Tae. J. Kwon (Supervisor), Dr. Karim El-Basyouny (Supervisory Committee Member), Dr. Fizzy Fan (Supervisory Committee Member), and Dr. Yuxiang Chen (Chair)