Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Comparative Study Between Decision Trees and Neural Networks to Predictfatal Road Accidents in Lebanon

Abstract : Nowadays, road traffic accidents are one of the leading causes of deaths in this world. It is a complex phenomenon leaving a significant negative impact on human’s life and properties. Classification techniques of data mining are found efficient to deal with such phenomena. After collecting data from Lebanese Internal Security Forces, data are split into training and testing sets using 10-fold cross validation. This paper aims to apply two different algorithms of Decision Trees C4.5 and CART, and various Artificial Neural Networks (MLP) in order to predict the fatality of road accidents in Lebanon. Afterwards, a comparative study is made to find the best performing algorithm. The results have shown that MLP with 2 hidden layers and 42 neurons in each layer is the best algorithm with accuracy rate of prediction (94.6%) and area under curve (AUC 95.71%).
Type de document :
Communication dans un congrès
Liste complète des métadonnées

https://hal.univ-angers.fr/hal-02517353
Contributeur : Marie-Françoise Gerard <>
Soumis le : mardi 24 mars 2020 - 15:03:12
Dernière modification le : mardi 24 mars 2020 - 15:05:44

Lien texte intégral

Identifiants

Collections

Citation

Zeinab Farhat, Ali Karouni, Bassam Daya, Pierre Chauvet. Comparative Study Between Decision Trees and Neural Networks to Predictfatal Road Accidents in Lebanon. 5th International Conference on Computer Science, Information Technology, Aug 2019, Vienne, Austria. pp.01-14, ⟨10.5121/csit.2019.91101⟩. ⟨hal-02517353⟩

Partager

Métriques

Consultations de la notice

223