RT info:eu-repo/semantics/conferenceObject
T1 Comparison of multivariate regression models and artificial neural networks for prediction highway traffic accidents in Spain: A case study
A1 Alqatawna, Ali
A1 Rivas Álvarez, Ana
A1 Sánchez-Cambronero García-Moreno, Santos
K1 Seguridad vial
K1 Road safety
K1 Tráfico
K1 Traffic
K1 Autopistas
K1 Highways
K1 Ingeniería civil
K1 Civil engineering
K1 Transportes
K1 Transportation
AB In recent years Spain shows the great reduction in the accident rate that has been achievedand the improvement of the behavior of road users, despite this, there is still a need toimprove many areas. In 2016 for the first time since the last 13 years, the number of fatalitiesincreased by 7% concerning to the previous year. In this paper, analysis and prediction ofroad traffic accidents (RTAs) of high accident locations highways in Spain, were undertakenusing Artificial Neural Networks (ANNs), which can be used for policymakers, this papercontributes to the area of transportation safety and researchers. ANN is a powerful techniquethat has demonstrated considerable success in analyzing historical data to forecast futuretrends.There are many ANN models for predicting the number of accidents on highways that weredeveloped using 4 years of data for accident counts on the Spain freeway roads from 2014to 2017. The best ANN model was selected for this task and the model variables involvedhighway sections, years, section length ,annual average daily traffic (AADT), the averagehorizontal curve radius, Slope gradient, traffic accidents with the number of heavy vehicles.In the ANN model development, the sigmoid activation function was employed with theLevenberg-Marquardt algorithm and the different number of neurons.The model results indicate the estimated traffic accidents, based on appropriate data are closeenough to actual traffic accidents and so are dependable to forecast traffic accidents in Spain.However, it demonstrates that ANNs provide a potentially powerful tool in analyzing andpredicting traffic accidents. The performance of the model was in comparison to themultivariate regression model developed for the same purpose. The results prove that theANN model stronger forecasted model which produced estimates fairly close to forecastfuture highway traffic accidents with Spanish conditions.
PB Universidad de Burgos. Servicio de Publicaciones e Imagen Institucional
SN 978-84-18465-12-3
YR 2021
FD 2021-07
LK http://hdl.handle.net/10259/7028
UL http://hdl.handle.net/10259/7028
LA eng
NO Trabajo presentado en: R-Evolucionando el transporte, XIV Congreso de Ingeniería del Transporte (CIT 2021), realizado en modalidad online los días 6, 7 y 8 de julio de 2021, organizado por la Universidad de Burgos
DS Repositorio Institucional de la Universidad de Burgos
RD 04-dic-2024