This study presents an innovative framework that integrates adaptive learning and cloud-based sensor fusion in order to improve the prediction of vehicle dynamics using passive data from vehicular sensors. The methodology aims to improve autonomous vehicles by harnessing relevant Advanced Driver-Assistance Systems (ADAS) features using real-time data from a network of vehicles to continuously improve predictive models. This system enhances the interpretation of data from many sources by combining sensor fusion and machine learning. By adapting to new information, it achieves precise real-time predictions. An optimization approach is introduced to streamline the implementation of cloud-based systems and minimize computational requirements. The effectiveness and adaptability of the framework surpasses those of conventional models, as demonstrated by empirical evidence. This highlights the capacity of the paradigm to radically revolutionize vehicle automation by allowing for more accurate prediction of vehicle dynamics. This study signifies an advancement in the enhancement of transportation that is both safer and more effective by utilizing collective data from vehicles to continuously improve and acquire knowledge.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Leveraging Vehicle Predictive Analytics through Adaptive Learning and Cloud-Aided Sensor Fusion


    Contributors:


    Publication date :

    2024-07-25


    Size :

    1121249 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English