CPSC 7460 - Machine Learning in Transportation Systems

(3) Credit Hours

This graduate-level course introduces the fundamental concepts of machine learning (ML) and their specialized applications in transportation systems. Topics include supervised and unsupervised learning, deep learning architectures, graph-based methods, and reinforcement learning techniques. Students will learn how to work with transportation-related datasets (traffic counts, speeds, travel times, GPS trajectories, transit ridership, ride-sharing data), explore data preprocessing and feature engineering specific to mobility scenarios, and develop modeling strategies to solve complex transportation problems (demand forecasting, traffic prediction, incident detection and route optimization). Through programming assignments and a research project, students will gain hands-on experience and produce a final deliverable that could lead to publication or real-world implementation. Prerequisites: CPSC 5440 or Department Head approval. Differential course fee will be assessed.

Effective Spring 2026.