This paper studies a problem of accurately predicting the time of passing traffic congestion. Through MATLAB programming, considering the relationship between traffic volume, traffic flow density, traffic flow speed and traffic congestion time, a new quantitative prediction method is established, that is, a multivariable BP neural network and time series coupling model (B-T). This mathematical model proposes a time period calculation method with different weights, which can combine the characteristics of BP neural network and time series to approximate the actual driving time as much as possible. The experiment shows that the proposed coupling model can maintain better prediction results under different traffic conditions and reduce the complexity of calculations. The workload has improved the actual engineering accuracy.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Model for Predicting the Time Through Traffic Jams


    Weitere Titelangaben:

    Lect. Notes Electrical Eng.


    Beteiligte:
    Hung, Jason C. (Herausgeber:in) / Chang, Jia-Wei (Herausgeber:in) / Pei, Yan (Herausgeber:in) / Wu, Wei-Chen (Herausgeber:in) / Zhou, Miao (Autor:in) / Pang, Jingxu (Autor:in) / Zeng, Wenjie (Autor:in) / Gao, Yuan (Autor:in) / Yang, Aimin (Autor:in)

    Erschienen in:

    Innovative Computing ; Kapitel : 143 ; 1167-1176


    Erscheinungsdatum :

    04.01.2022


    Format / Umfang :

    10 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Look, Ma'am, No Traffic Jams!

    Skousen, Mark | Wiley | 2012


    Solution to airport traffic jams

    Litchford, G. / Lyman, J. | Engineering Index Backfile | 1950


    Street cars or traffic jams?

    Johnson, W.D. | Engineering Index Backfile | 1932


    Traffic jams and the congestion toll

    Mun, Se-Il | Online Contents | 1994