Randomized trial examines travel time prediction in urban traffic management, suggesting advanced solutions.
Key Points
This research aims to enhance urban traffic management through a hybrid framework combining AI and Digital Twin technology for better travel time prediction.
Developed a data-driven framework integrating RNNs with Digital Twin technology.
Utilized real-time and historical data from Google Maps, weather services, and traffic sensors.
Conducted comparative analysis to evaluate performance against conventional navigation tools.
RNN model achieved a predictive accuracy with R² value of approximately 0.94.
DT system demonstrated a 26% reduction in travel time compared to traditional tools in congested scenarios.