Memorias de investigación
Capítulo de libro:
Covariates selection for predicting collisions and run-off accidents in Spanish interurban network using tree-based models
Año:2016

Áreas de investigación
  • Ingenierías

Datos
Descripción
In this work we use classification tree based-models for pattern identification and analysis as well as prediction of accident typology in 2010, 2011 and 2012 years in the Spanish interurban roads. The models are mainly used to describe and understand the underlying relationship between accident type and predictor variables comprising functional road type, accident scenario characteristics as well as traffic information as the average speed of light vehicles; second for fitting a model with high prediction accuracy of new cases, and third for extracting if-then rules from a small group of predictors so that some clusters are obtained associated to the accident type (run-off-road collision and collision between two vehicles travelling in opposite directions).
Internacional
No
DOI
Edición del Libro
1
Editorial del Libro
FUNDACIÓN GENERAL DE LA UPM
ISBN
978-84-16397-46-4
Serie
Título del Libro
Proceedings of the First Symposium SEGVAUTO-TRIES-CM. Technologies for a Safe, Accessible and Sustainable Mobility. R&D+I in Automotive: RESULTS
Desde página
123
Hasta página
127

Esta actividad pertenece a memorias de investigación

Participantes

Grupos de investigación, Departamentos, Centros e Institutos de I+D+i relacionados
  • Creador: Grupo de Investigación: Estadística computacional y Modelado estocástico
  • Departamento: Ingeniería Mecánica
  • Departamento: Ingeniería de Organización, Administración de Empresas y Estadística