Many models of trip attraction based on land utilization ignore the differences among land utilization weight factors of different traffic zones. In this paper, a trip attraction prediction model, which clusters the land utilization, is studied. Considering the distinctions among the land utilizations of traffic zones, the traffic zones are classified into dissimilar groups by dynamic clustering analysis with principal component scores. Then, land utilization weight factors are calibrated by groups using regression analysis, until all types of land utilization included in different traffic zones of dissimilar groups are endowed with corresponding weight factors. The main parameter adopted here is "Importance of Traffic Zone". Finally, the trip attracting volume can be predicted. With a numerical example using the data collected in a field investigation in TongLing City, it is verified that the model has better accuracy and practicality.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Prediction Model of Trip Attraction Based on Clustering of Land Utilization


    Beteiligte:
    Dai, Guangyuan (Autor:in) / Wang, Wei (Autor:in) / Zhao, De (Autor:in)

    Kongress:

    Second International Conference on Transportation Information and Safety ; 2013 ; Wuhan, China


    Erschienen in:

    ICTIS 2013 ; 441-448


    Erscheinungsdatum :

    11.06.2013




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    A methodology and proposal for retail trip attraction model

    Fadda, P. / Fancello, G. | British Library Conference Proceedings | 1998


    Trip production and attraction characteristics in small cities

    Harmelink, M.D. / Harper, G.C. / Edwards, H.M. | Engineering Index Backfile | 1967


    Traffic network design model with trip production-attraction and supply uncertainty

    Yu, Xinxin / Bian, Changzhi / Han, Xianke et al. | SPIE | 2024