Manhattan Traffic
Home
Table of Contents
In this project, we analyze Manhattan taxi-traffic using a constrained nonnegative matrix factorization algorithm that promotes sparsity and allows us to decompose traffic into a linear combination of 50 distinct traffic signatures.
- GitLab code repository
- gitlab-beta.engr.illinois.edu/TrafficPatterns/CSNMF
- Original data files
- doi.org/10.13012/B2IDB-4900670V1
- to appear in the Journal of Big Data Analytics in Transportation
- Seasonal Disorder in Urban Traffic Patterns: a low rank analysis
A manuscript for this project is set to be published been submitted for publication and is pending review.
The congestion barcodes project was an offshoot of this work.
1. Collaborators
- Richard Sowers
- Daniel B. Work
- Derrek Yager
- Marzieh Abolhelm