Forecasting Adverse Weather Situations in the Road Network
Impacto
Scholar |
Otros documentos de la autoría: Tomás, Vicente R.; Pla-Castells, Marta; Martínez, Juan José; Martínez-Cantó, Javier
Metadatos
Mostrar el registro completo del ítemcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/8620
comunitat-uji-handle4:
INVESTIGACIONEste recurso está restringido
http://dx.doi.org/10.1109/TITS.2016.2519103 |
Metadatos
Título
Forecasting Adverse Weather Situations in the Road NetworkFecha de publicación
2016-08Editor
Institute of Electrical and Electronics Engineers (IEEE)ISSN
1524-9050; 1558-0016Cita bibliográfica
TOMÁS, Vicente R., et al. Forecasting Adverse Weather Situations in the Road Network. IEEE Transactions on Intelligent Transportation Systems, 2016, vol. 17, no 8, p. 2334-2343.Tipo de documento
info:eu-repo/semantics/articleVersión de la editorial
http://ieeexplore.ieee.org/abstract/document/7438821/Versión
info:eu-repo/semantics/publishedVersionPalabras clave / Materias
Resumen
Weather is an important factor that affects traffic flow and road safety. Adverse weather situations affect the driving conditions directly; hence, drivers must be informed about the weather conditions downstream to ... [+]
Weather is an important factor that affects traffic flow and road safety. Adverse weather situations affect the driving conditions directly; hence, drivers must be informed about the weather conditions downstream to adapt their driving. In the framework of intelligent transport systems, several systems have been developed to know the weather situations and inform drivers. However, these systems do not forecast weather in advance, and they need the support of road operators to inform drivers. This paper presents a new autonomous system to forecast weather conditions in a short time and to give users the information obtained. The system uses a set of algorithms and rules to determine the weather and to forecast dangerous situations on the road network. It has been implemented using a multiagent approach and tested with real data. Results are very promising. The system is able to forecast adverse situations with a high degree of quality. This quality makes it possible to trust in the system and to avoid the supervision of operators. [-]
Publicado en
IEEE Transactions on Intelligent Transportation Systems, 2016, vol. 17, no 8, p. 2334-2343Derechos de acceso
Aparece en las colecciones
- ICC_Articles [430]