Zhengbing He

Professor in Autonomous and Intelligent Systems
University of Nottingham Ningbo China

Google Scholar GitHub LinkedIn Email: he dot zb at hotmail dot com
Office: IAMET 322, UNNC Campus

Traffic Flow Theory

Traffic Flow Theory (CIVE5490, Department of Civil & Environmental Engineering at the University of Massachusetts Lowell, 2024–2025) is a foundational course that focuses on traffic dynamics and the essential mathematical models and tools used to analyze and predict vehicle movement and traffic congestion on roadways. The course provides a solid understanding of key concepts such as vehicle trajectories, capacity drop, fundamental diagrams. It particularly covers important models and tools, including car-following models, lane-changing models, kinematic wave theory, and cumulative count curves. These concepts and tools form the foundation for various studies and applications in transportation engineering and traffic management. Download: https://github.com/gotrafficgo/traffic_flow_theory_slides

0. Introduction to traffic flow theory
1. Trajectories and microscopic traffic variables
2. Macroscopic traffic variables
3. Important traffic characteristics
4. Kinematic wave theory
5. Cumulative count curve and queueing analysis
6. Cellular automata
7.1 Car-following models: Basic
7.2 Car-following models: Gipps model
8.1 Car-following models: Newell model
8.2 Car-following models: Data-driven model
9.1 Lane-changing models: Basic
9.2 Lane-changing models: Data-driven
10.1 Intersection control: Basic
10.2 Intersection control: Future
11.1 Emerging Technologies: Stop-and-Go Wave Suppression

Applications of AI in EEE

Applications of AI in EEE (EEEE3134, Department of Electrical & Electronic Engineering at the University of Nottingham Ningbo China, 2026–Present) introduces artificial intelligence to engineering students. The course emphasizes concepts and applications, treating AI as an engineering tool. Students explore modern programming workflows using Python, VS Code, Git/GitHub, and AI-assisted development tools, then apply these skills to autonomous-driving models. The course also covers machine learning, supervised and unsupervised learning, and deep learning, including large language models (LLMs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). Practical exercises and a final project develop students’ ability to construct and validate an AI model and communicate its performance through a report and presentation. Download: https://github.com/gotrafficgo/teaching_artificial_intelligence

0. Course introduction and syllabus
1. Artificial intelligence: Concepts and historical development
2. Modern programming: Python and VS Code
3. Modern programming: Git, GitHub, and AI Agent
4. Autonomous driving: Concepts and historical development
5. Autonomous driving: Vehicle longitudinal motion modeling
6. Autonomous driving: Gipps model
7. Autonomous driving: kNN-driven modeling
8. The landscape of AI technologies
9. What does machine learning learn?
10. Large language models (LLMs)
11. Convolutional neural networks (CNNs)
12. Recurrent neural networks (RNNs)
13. Reinforcement Learning (RL)