According to World Health Organization, each year, over 1.2 million people die on roads, and between 20 and 50 million suffer non-fatal injuries. Based on international reports, Iran has a high death rate caused by road accidents. The objective of this study was to extract implicit knowledge from road accident data sets on roads of Iran through data mining. In this regard, three useful data mining techniques were combined: clustering, classification and rule extraction. Following the preparation stage, data were segmented via three clustering algorithms; Kohonen, K-Means and Twostep. Two-step cluster analysis is a one-pass-through data approach which generates a fairly large number of pre-clusters. Next, the optimized algorithm and cluster were identified, after which, in the classification level and by adding the drivers' demographic features through C5.0, a classification algorithm was employed so as to make the decision tree. Ultimately, the effects of these demographic features were investigated on road accidents. The characteristics such as age, job, driving license duration and gender proved to be more important factors in accident analysis. Certain rules of accidents were then extracted in each season of the year.


    Access

    Download


    Export, share and cite



    Title :

    The Effect of Drivers' Demographic Characteristics on Road Accidents in Different Seasons Using Data Mining


    Contributors:


    Publication date :

    2017




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown





    Study on Road Accidents Using Data Mining Technology

    Johnson, Emi / Abraham, Juby Mary / Sulaiman, Sameera et al. | IEEE | 2018


    Analysis of Road Accidents Using Data Mining Paradigm

    John, Maya / Shaiba, Hadil | Springer Verlag | 2021


    Papers - Road accidents caused by drivers falling asleep

    Sagberg, Fridulv | Online Contents | 1999


    Using hybrid Data Mining algorithm for Analysing road accidents Data Set

    Parathasarathy, G. / Soumya, T.R / Das, Y. Justin et al. | IEEE | 2019