The goal of this research is to develop a machine learning framework to predict the spatiotemporal impact of traffic accidents on the upstream traffic and surrounding region. We propose a Latent Space Model for Road Networks (LSM-RN), which enables more accurate and scalable traffic prediction by utilizing both topology similarity and temporal correlations. Our framework further enables real-time traffic prediction by 1) exploiting real-time sensor readings to adjust/update the latent spaces, and 2) training as data arrives and predicting on-the-fly.
Analysis and Prediction of Spatiotemporal Impact of Traffic Incidents for Better Mobility and Safety in Transportation Systems, Research Project
2015
2 pages
Report
Keine Angabe
Englisch
Analysis of Spatiotemporal Impact of Traffic Incidents on Road Networks
Springer Verlag | 2022
|Analysis of Spatiotemporal Impact of Traffic Incidents on Road Networks
British Library Conference Proceedings | 2022
|