Descripción
|
|
---|---|
The purpose of this paper is to apply two different statistical methodologies, decision trees and logistic regression, to the analysis of the severity of road accidents along two high-use interurban freight corridors in Spain, Madrid-Irún and Barcelona-Almería. The two corridors mentioned above are part of two international rail freight Corridors across Spain and are considered as possible subjects of policy freight transport policy changes, namely the shift from road to rail to increase safety and decrease emissions [1]. The interest of the analysis relies to a certain extent in comparing the results of two different statistical approaches since decision trees are a non-parametric, machine learning sort of technique, while logistic regression is a traditional parametric approach. The study has focused on four different crash types: headon crashes, angle crashes, sideswipe crashes and rear-end crashes. The explanatory variables introduced in the models can be classified in roadway design characteristics, driver related behavior, location and state of road variables. | |
Internacional
|
No |
Nombre congreso
|
FUNDACIÓN GENERAL DE LA UPM |
Tipo de participación
|
960 |
Lugar del congreso
|
|
Revisores
|
Si |
ISBN o ISSN
|
978-84-16397-46-4 |
DOI
|
|
Fecha inicio congreso
|
17/11/2016 |
Fecha fin congreso
|
18/11/2016 |
Desde la página
|
119 |
Hasta la página
|
122 |
Título de las actas
|
Proceedings of the First Symposium SEGVAUTO-TRIES-CM. Technologies for a Safe, Accessible and Sustainable Mobility. R&D+I in Automotive: RESULTS |