Academy & Industry Research Collaboration Center (AIRCC)

Volume 9, Number 11, August 2019

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

  Authors

Zeinab Farhat1, Ali Karouni2, Bassam Daya2 And Pierre Chauvet3, 1Edst, Lebanese University, Lebanon, Beirut, 2University Institute Of Technology, Lebanese University, Lebanon, Sidon and 3Laris Ea, Angers University France, France, Angers

  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%).

  Keywords

Data mining, Fatal Road Accident Prediction, Neural Networks, Decision trees