PROJECT TITLE :

Low-Dimensional Models for Compressed Sensing and Prediction of Large-Scale Traffic Data

ABSTRACT:

Advanced sensing and surveillance technologies typically collect traffic information with high temporal and spatial resolutions. The volume of the collected data severely limits the scalability of online traffic operations. To overcome this issue, we propose a low-dimensional network illustration where only a subset of road segments is explicitly monitored. Traffic info for the subset of roads is then used to estimate and predict conditions of the whole network. Numerical results show that such approach provides 10 times faster prediction at a loss of performance of threepercent and onepercent for five- and thirty-min prediction horizons, respectively.