RefDoc
Haut

Faire une nouvelle recherche
Make a new search
Lancer la recherche


Titre du document / Document title

Predicting injury severity levels in traffic crashes: A modeling comparison

Auteur(s) / Author(s)

ABDEL-ATY Mohamed A. (1) ; ABDELWAHAB Hassan T. (1) ;

Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)

(1) Dept. of Civil and Environmental Engineering, Univ. of Central Florida, Orlando, FL 32816-2450, ETATS-UNIS

Résumé / Abstract

This paper investigates the use of two well-known artificial neural network (ANN) paradigms: the multilayer perceptron (MLP) and fuzzy adaptive resonance theory (ART) neural networks in analyzing driver injury severity. The objective of this study is to investigate the viability and potential benefits of using the ANN in predicting driver injury severity conditioned on the premise that a crash has occurred. The performance of the ANN was compared to a calibrated ordered probit model. Modeling results showed that the testing classification accuracy was 73.5% for the MLP, 70.6% for the fuzzy ARTMAP, and 61.7% for the ordered probit model. This result indicates a more accurate prediction capability of injury severity for ANN (particularly the MLP) over other traditional methods. The results of the models showed that gender, vehicle speed, seat belt use, type of vehicle, point of impact, and area type (rural versus urban) affect the likelihood of injury severity levels.

Revue / Journal Title

Journal of transportation engineering    ISSN  0733-947X   CODEN JTPEDI 

Source / Source

2004, vol. 130, no2, pp. 204-210 [7 page(s) (article)] (21 ref.)

Langue / Language

Anglais

Editeur / Publisher

American Society of Civil Engineers, Reston, VA, ETATS-UNIS  (1983) (Revue)

Mots-clés anglais / English Keywords

Simulation model

;

Probit model

;

Neural network

;

Severity score

;

Injury

;

Forecast model

;

Modeling

;

Comparative study

;

Traffic accident

;

Road traffic

;

Mots-clés français / French Keywords

Modèle simulation

;

Modèle probit

;

Réseau neuronal

;

Indice gravité

;

Blessure

;

Modèle prévision

;

Modélisation

;

Etude comparative

;

Accident circulation

;

Trafic routier

;

Mots-clés espagnols / Spanish Keywords

Modelo simulación

;

Modelo probit

;

Red neuronal

;

Indicio gravedad

;

Herida

;

Modelo previsión

;

Modelización

;

Estudio comparativo

;

Accidente tráfico

;

Tráfico carretera

;

Mots-clés d'auteur / Author Keywords

Traffic accidents

;

Injuries

;

Neural networks

;

Comparative studies

;

Models

;

Localisation / Location

INIST-CNRS, Cote INIST : 572 E, 35400011350510.0070

Nº notice refdoc (ud4) : 15533208



Faire une nouvelle recherche
Make a new search
Lancer la recherche
Bas