Analysis and Prediction of Spatiotemporal Impact of Traffic Incidents for Better Mobility and Safety inTransportation Systems
Cyrus Shahabi, Ugur Demiryurek · 2015
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. The main objective of the framework is, given a road accident, to forecast when and how the travel-time delay will occur on transportation network. Towards this end, the authors have developed a Dynamic Topology-aware Temporal (DTT) machine learning algorithm that learns the behavior of traffic in both normal conditions and during accidents from the historical traffic sensor datasets. This research exploits four years of real-world Los Angeles traffic sensor data and California Highway Patrol (CHP) accidents logs collected from Regional Integration of Intelligent Transportation Systems (RIITS) under Archived Traffic Data Management System (ADMS) project.