The UTC Graduate School is pleased to announce that Jewel Rana Palit will present Master’s research titled, APPLICATION OF PREDICTIVE MODELING TO SUPPORT TRAFFIC INTERSECTION CONTROL AND SAFETY on 10/12/2022 at 11:00 AM-12:00 PM in EMCS 426. Everyone is invited to attend.
Engineering
Chair: Weidong Wu
Co-Chair: Mina Sartipi
Abstract:
The exponential traffic growth hasn’t been well-handled by traditional control systems. Adaptive controls are necessary at signalized intersections since they foresee traffic demand based on predictive modeling and make decisions ahead of time. Predictive modeling can also boost traffic safety by foreseeing near-crash events leveraging cutting-edge datasets like LiDAR. This thesis addresses effective intersection control and safety by developing prediction models based on emerging traffic datasets. A novel deep learning model called MGCNN is suggested for short-term turning movements prediction using GRIDSMART data from the MLK corridor in Chattanooga. During assessments for 1 to 5-minute future prediction, MGCNN surpasses contemporary models with 0.9 MSE. Traditional machine learning models are applied efficiently for forecasting speed and arrival at green with MSE of 0.04 and 0.05. Hybrid Convolutional Gated Recurrent Neural Network model is proposed for near-crash prediction that shows 100% recall, precision, and F1-score: accurately predicting all near-crashes based on LiDAR data from Georgia intersection of MLK. These modeling methodologies provide scopes for better intersection control and safety via AI applications in Intelligent Transportation Systems.