Abstract The development of floating car technology provides a new method for studying driving behavior motivation. Massive vehicle trajectory data often contains rich potential semantic information such as traffic patterns and driving behavior habits. To overcome the nonstationarity of the spatial distribution of the original trajectory data, this paper designs a semantic mining method of traffic trajectory data to construct complex behavioral modeling of traffic trajectory data based on LDA latent semantic topic model, so that to depict the driving behavior interest patterns and explore the cognitive mechanism of driving behavior. Research results show that the driving motivation model constructed can estimate the probability of the potential driving motivation topic in each spatial grid, and then the driving trajectory will be transformed from random probability events into driving intention with intrinsic certainty.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Driving Behavior Motivation Model Research Based on Vehicle Trajectory Data


    Beteiligte:
    Chen, Yun (Autor:in) / Jiang, Xin-hua (Autor:in) / Liao, Lyuchao (Autor:in) / Zou, Fu-min (Autor:in) / Zhang, Mei-run (Autor:in)


    Erscheinungsdatum :

    03.11.2017


    Format / Umfang :

    9 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Research on vehicle behavior prediction based on high precision trajectory data

    Zhang, Jiayu / Wu, Xianyu | British Library Conference Proceedings | 2023



    ANALYSIS OF TAXI DRIVING BEHAVIOR AND DRIVING RISK BASED ON TRAJECTORY DATA*

    Fan, Jing / Li, Ye / Liu, Yuanlin et al. | British Library Conference Proceedings | 2019


    Analysis of taxi driving behavior and driving risk based on trajectory data *

    Fan, Jing / Li, Ye / Liu, Yuanlin et al. | IEEE | 2019