Connected Cities for Smart Mobility toward Accessible and Resilient Transportation
The increasing popularity of smart cities and recent developments in sensing, edge computing and vehicle technologies and the availability of “big data” combined with sophisticated AI techniques offer an opportunity
3On February 22, 2023, New York University and Tongji University are joining forces to host an online urban transportation forum. The topics to be covered in this virtual event include
Instructor: Fan Zuo, New York University Schedule: Friday March 10, 11:00am-12:00pm Description: In this course, you will learn about ChatGPT, a state-of-the-art language model developed by OpenAI. You will gain
Graph Neural Networks (GNNs) are a powerful tool for analyzing and processing graph-structured data. This course covers the basics of GNNs, including graph convolutional networks, graph attention networks and graph wavelet networks, including how they work and how to implement them. The session aims to provide a solid understanding of GNN modeling for machine learning practitioners, data scientists, and anyone interested in AI advancements.
The C2SMART Center and the NYU chapter of the Institute of Transportation Engineers (ITE) are excited to host our annual Women in Transportation Panel Discussion, including an opportunity for attendees to network and socialize. This year's panel boasts three amazing women working in the transportation industry who will share their perspectives and experiences.
In this hands-on course, you’ll learn how to use Unity 3D to build 3D models of road networks. You’ll start with the basics of Unity 3D, including its interface, GameObjects, components, and scripting. From there, you’ll dive into building 3D models of road networks, covering elements such as roads, buildings, and terrain.
Dr. Lili Du will discuss the EP fleet management problem, which is mathematically modeled as a vehicle routing problem (i.e., mE2-VRP), aiming to optimally dispatch the minimum number of EPs to approach and serve the EDs using different proportions of EV flows to save EDs’ travel time and mitigate traffic congestion to different extents in different network congestion and charging station coverage scenarios. She will also discuss suggestions for improving the service efficiency of CaaS + .
This course covers the basics of graph neural networks (GNNs), including graph convolutional networks, graph attention networks and graph wavelet networks. The session aims to provide a solid understanding of GNN modeling for machine learning practitioners, data scientists, and anyone interested in AI advancements.
In this course, you will learn how to harness the power of OSMnx, a Python library for extracting and visualizing Open Street Maps data. Through hands-on exercises, you will gain practical experience in using OSMnx to model and simulate projects and have a solid understanding of this Python library and be able to apply OSMnx to real-world problems.
In transportation planning, volume-delay functions (VDFs) are essential functions used for traffic assignment and network design problems. However, the static Bureau of Public Roads (BPR) function, created by the
C2SMART is thrilled to welcome members of faculty from KAIST (Korea Institute for Advanced Study of Science and Technology).
COVID has exacerbated two emerging trends in transportation analysis: (1) the rise of passively-generated big data; and (2) the increasing need to deal with the “unexpected” disruptions. This talk emphasizes the need for learning big and small data for transportation planning and resilience analysis. Different ways of learning are described, with applications ranging from long-term planning analysis to rapid responses under disruptions.