Guang Wang
Florida State University, FL·Computer Science
Data on how people move through cities can help researchers study traffic, plan neighborhoods, track disease spread and understand economies. Most of this mobility data, however, is owned by companies.
- Fields
Computer Science
Engineering
Social Science
- Topics
mobility data
human mobility
synthetic data
- Grants
- 1 known grant, through Jun 2027
What they work on
- Build cross-domain data curation tools for MobilityNet that combine real mobility datasets from different sources to reduce data bias.
- Develop socially informed methods to interpret real mobility data, drawing on user studies to recover meaning that movement records leave implicit.
- Generate realistic synthetic mobility data using generative machine learning with differential privacy, a mathematical privacy guarantee, and evaluate its utility, privacy and fairness with measurable metrics.
- Share the synthetic mobility data with 19 partners across transportation, urban planning, geography, epidemiology and economics.
More about the research
It is costly or impossible to obtain, and sharing it raises serious privacy concerns. This project asks whether realistic synthetic, or artificial, mobility data can stand in for the real thing. The goal is data that is useful to researchers, protects individual privacy, and treats different groups fairly.
Why it matters
Researchers who study traffic, city planning, disease spread and economics often cannot get detailed human movement data because it is private and proprietary. Privacy-protecting synthetic mobility data could give these fields realistic data to work with while lowering the risk of exposing individuals. The project also aims to reduce bias so that results reflect diverse populations fairly.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Vishnu Boddeti
Michigan State University, MI·Computer Science
Derive theoretical limits on the trade-offs among predictive accuracy, robustness across patient populations and privacy in healthcare AI models, and evaluate them in practice.
Constantine Kontokosta
New York University, NY·Social Science
Identify representativeness bias in smartphone mobility data, meaning which groups are over- or undercounted, and develop methods to correct it.
Shuangqing Wei
Louisiana State University, LA·Engineering
Generate a synthetic video dataset of tracheostomy-dependent infants to train privacy mechanisms, identity separation and recombination systems, and classifiers when real patient video is scarce.
The school
Florida State University: 15 labs on PI Pages, $461M a year on research, 481 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.