Title :
AOID: adaptive on-line incident detection system
Author :
Boedihardjo, Arnold P. ; Lu, Chang-Tien
Author_Institution :
Dept. of Comput. Sci., Virginia Polytech. Inst. & State Univ.
Abstract :
The provisions of any emergency management system with respect to the public safety necessitates the inclusion of the transportation network. The transportation network provides a means for mitigation strategies for any disaster, whether it is natural or human-induced. In this paper, we introduce a set of tools to integrate with a traffic information system to provide automatic traffic incident detection and traffic forecast. Current automated incident detection techniques may not perform well under changing traffic patterns, recurrent congestions, and may require large amounts of training data. We propose a solution to mitigate these shortcomings by utilizing predicted traffic models and performing comparative analysis against observed traffic patterns to automatically detect incidents
Keywords :
disasters; emergency services; traffic information systems; adaptive online incident detection system; automatic traffic incident detection; data analysis; data mining; emergency management system; intelligent highway system; public safety; traffic forecast; traffic information system; traffic pattern; transportation network; Disaster management; Management information systems; Pattern analysis; Performance analysis; Predictive models; Safety; Telecommunication traffic; Traffic control; Training data; Transportation;
Conference_Titel :
Intelligent Transportation Systems Conference, 2006. ITSC '06. IEEE
Conference_Location :
Toronto, Ont.
Print_ISBN :
1-4244-0093-7
Electronic_ISBN :
1-4244-0094-5
DOI :
10.1109/ITSC.2006.1706851