Open AccessIdentifying Efficient Road Safety Prediction Model Using Data Mining Classifiers
Author(s) -
Durga Karthik,
P. Karthikeyan,
S. Kalaivani,
K. Vijayarekha
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.a1018.0881019
Subject(s) - c4.5 algorithm , computer science , random forest , naive bayes classifier , accident (philosophy) , collision , bayesian network , traffic accident , multivariate statistics , predictive modelling , data mining , machine learning , transport engineering , engineering , computer security , support vector machine , philosophy , epistemology
Road accidents are a major cause of death and disabilities. The aim of the traffic accident analysis for a region is to investigate the cause for accidents and to determine dangerous locations in a region. Multivariate analysis of traffic accidents data is critical to identify major causes for fatal accidents. In this work, accident dataset is analysed using algorithmic approach, as an attempt to address this problem. The relationship between fatal rate and other attributes including collision manner, weather, surface condition, light condition, mobile users and drunken driving are considered. Prediction model using various data mining classifiers such as Bayesian, J48, Random Forest will be constructed to enhance safety regulations for a region.