Abstract We propose IR-CAS ACN, a fully Automated Crash Notification safety application that enhances accuracy and efficiency with its precise notifications and increased decentralization. It can be considered as an improvement to the BMW Advanced ACN (AACN): It decentralizes the severity calculation by introducing in-vehicle severity estimation. It fully automates the solution and disseminates more informative messages with partial rather than graded relevance that is insensitive to differences in severity within grades. Different IR models are compared using binary and partial effectiveness measures; estimating severity by calculating the Manhattan distance between the crash and severest crash context vectors outperforms tried models.
VANET IR-CAS for Safety ACN: Information Retrieval Context Aware System for VANET Automatic Crash Notification Safety Application
International Journal of Intelligent Transportation Systems Research ; 14 , 3 ; 127-138
2014-12-05
12 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Survey on Context-Aware Publish/Subscribe Systems for VANET
Springer Verlag | 2013
|Survey on Context-Aware Publish/Subscribe Systems for VANET
British Library Conference Proceedings | 2013
|Event Notification in VANET With Capacitated Roadside Units
Online Contents | 2016
|