Spatio-temporal data prediction using GCN-based GAN
In this project, we aim to develop GCN-based GAN models to predict spatio-temporal evolution using open human mobility datasets – SafeGraph (https://www.safegraph.com/).
M.S. are welcome to register my research credits during the semesters and summer. The student involved in this project will develop GAN based models that can predict. spatio-temporal evolution of human mobility. Students with coding skills and past experience in analyzing spatio-temporal data and training GAN and GCN/GNN models are preferred. Skill requirements are:
- Familiar with Python. Generating figures, graphs, tables, or statistical models to present results with python.
- Familiar with GAN and its variant models.
- Familiar with GCN/GNN.
- Having past experience in doing research and demonstrating independent research capabilities.
This is an UNPAID research project.
Faculty Advisor
- Professor: Sharon Di
- Center/Lab: Civil Engineering
- Location: Morningside Mudd
- selfdriving, AI
Project Timeline
- Earliest starting date: 1/24/2023
- End date: 12/24/2023
- Number of hours per week of research expected during Spring-Summer 2023: ~15
Candidate requirements
- Skill sets: big data processing, programming, GAN training
- Student eligibility:
freshman,sophomore,junior,senior, master’s - International students on F1 or J1 visa: eligible
- Academic Credit Possible: Yes