The Internet of Things (IoT) has been growing in recent years with the improvements in several different applications in the military, marine, intelligent transportation, smart health, smart grid, smart home and smart city domains. Although IoT brings significant advantages over traditional information and communication (ICT) technologies for Intelligent Transportation Systems (ITS), these applications are still very rare. Although there is a continuous improvement in road and vehicle safety, as well as improvements in IoT, the road traffic accidents have been increasing over the last decades. Therefore, it is necessary to find an effective way to reduce the frequency and severity of traffic accidents. Hence, this paper presents an intelligent traffic accident detection system in which vehicles exchange their microscopic vehicle variables with each other. The proposed system uses simulated data collected from vehicular ad-hoc networks (VANETs) based on the speeds and coordinates of the vehicles and then, it sends traffic alerts to the drivers. Furthermore, it shows how machine learning methods can be exploited to detect accidents on freeways in ITS. It is shown that if position and velocity values of every vehicle are given, vehicles' behavior could be analyzed and accidents can be detected easily. Supervised machine learning algorithms such as Artificial Neural Networks (ANN), Support Vector Machine (SVM), and Random Forests (RF) are implemented on traffic data to develop a model to distinguish accident cases from normal cases. The performance of RF algorithm, in terms of its accuracy, was found superior to ANN and SVM algorithms. RF algorithm has showed better performance with 91.56% accuracy than SVM with 88.71% and ANN with 90.02% accuracy.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Traffic accident detection using random forest classifier


    Beteiligte:


    Erscheinungsdatum :

    2018-02-01


    Format / Umfang :

    498658 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Traffic accident risk studying and judging method based on interpretable random forest

    WAN YUJIE / DONG CHUNJIAO / LI PENGHUI et al. | Europäisches Patentamt | 2024

    Freier Zugriff


    Traffic accident detection device and method of detecting traffic accident

    EMURA KOICHI | Europäisches Patentamt | 2017

    Freier Zugriff


    Complexity Reduction Using the Random Forest Classifier in a Collision Detection Algorithm, pp. 1228-1235

    Lauer, C. / Botsch, M. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2010