Traffic-related fatalities, often caused by human error, present a global challenge. Autonomous vehicles (AVs), designed to reduce these fatalities by eliminating human error, still experience crashes. Prior research, limited by the scope of the data set and analytical depth, has not fully explored these factors, resulting in a lingering lack of clarity about the cause of the crashes. The study utilized a comprehensive dataset spanning from 2014 to May 2024 and implemented a stratified sampling alongside class weighting techniques to rectify imbalances within the crash data. A variety of machine learning algorithms such as logistic regression, decision trees, random forests, gradient boosting, bagging classifiers, and easy ensemble methods were utilized to perform the data analysis. The random forest model stood out for its balance in sensitivity and specificity, reducing false negatives. The study revealed that factors such as the extent of vehicle damage, the AV manufacturer, and type of collision were critical predictors of crash injuries. The research provides valuable insights for various stakeholders, including transportation professionals, AV manufacturers, and policymakers. The findings can guide the development of enhanced safety protocols, improved vehicle designs, and more informed policy frameworks aimed at reducing AV-related injuries.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Predictive analytics in autonomous vehicles safety: crash outcome modeling


    Weitere Titelangaben:

    S. S. CHANNAMALLU ET AL.
    URBAN, PLANNING AND TRANSPORT RESEARCH




    Erscheinungsdatum :

    31.12.2024


    Format / Umfang :

    20 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Predictive analytics in autonomous vehicles safety: crash outcome modeling

    Sai Sneha Channamallu / Deema Almaskati / Sharareh Kermanshachi et al. | DOAJ | 2024

    Freier Zugriff

    Predictive Analytics for Modeling UAS Safety Risk

    Luxhoj, James T. | SAE Technical Papers | 2013


    Predictive Analytics for Modeling UAS Safety Risk

    Luxhoj, J.T. / Society of Automotive Engineers | British Library Conference Proceedings | 2013



    Autonomous Vehicles Camera Blinding Attack Detection Using Sequence Modelling and Predictive Analytics

    Sharath Yadav, D. H. / Ansari, Asadullah | British Library Conference Proceedings | 2020