The publication includes a review of information on the methods of pavement condition recognition using various methods. Measurement system has been presented that allows to determine the condition of the pavement using the Inertial Measurement Unit (IMU) and machine learning methods. Three machine learning methods were considered: random forest, gradient boosted tree and custom architecture neural network (roadNet). Due to the developed system the set of learning and validation data was created on 3 vehicles: Opel Corsa, Honda Accord, Volkswagen Passat. All of the listed vehicles have front wheel drive. The presented machine learning methods have been compared with each other. The best accuracy on the validation set was achieved by the artificial neural network (ANN). The study showed that asphalt condition classification is possible and the developed system fulfils its task.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Classification of the Condition of Pavement with the Use of Machine Learning Methods


    Beteiligte:
    Tomiło Paweł (Autor:in)


    Erscheinungsdatum :

    2023




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    Ensemble Machine Learning Classification Models for Predicting Pavement Condition

    Chung, Frederick / Doyle, Andy / Robinson, Ernay et al. | Transportation Research Record | 2024


    Assessment of Present Pavement Condition Using Machine Learning Techniques

    Sharma, Madhavendra / Kumar, Pradeep | TIBKAT | 2022


    Pavement Condition

    Bektas, Faith / Smadi, Omar / Nlenanya, Inya | Transportation Research Record | 2019


    NDT Seismic Methods in Pavement Condition Assessment

    Gucinski, N. / Maher, M. H. / American Society of Civil Engineers et al. | British Library Conference Proceedings | 1995


    Airport pavement condition assessment methods and apparatuses

    BISHOP GRANT / SAUR VALERIE / LU SHIHLIN et al. | Europäisches Patentamt | 2023

    Freier Zugriff