This study presents a data segmentation method, which was intended to improve the performance of the k-nearest neighbours algorithm for making short-term traffic volume predictions. According to the introduced method, selected segments of vehicle detector data are searched for records similar to the current traffic conditions, instead of the entire database. The data segments are determined on the basis of a segmentation procedure, which aims to select input data that are useful for the prediction algorithm. Advantages of the proposed method were demonstrated in experiments on real-world traffic data. Experimental results show that the proposed method not only improves the accuracy of the traffic volume prediction, but also significantly reduces its computational cost.


    Access

    Access via TIB


    Export, share and cite



    Title :

    Segmentation of vehicle detector data for improved k-nearest neighbours-based traffic flow prediction


    Contributors:

    Published in:

    Publication date :

    2015-04-01


    Size :

    11 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Segmentation of vehicle detector data for improved k‐nearest neighbours‐based traffic flow prediction

    Bernaś, Marcin / Płaczek, Bartłomiej / Porwik, Piotr et al. | Wiley | 2015

    Free access

    Short‐term traffic forecasting using self‐adjusting k‐nearest neighbours

    Sun, Bin / Cheng, Wei / Goswami, Prashant et al. | Wiley | 2018

    Free access

    Short-term traffic forecasting using self-adjusting k-nearest neighbours

    Sun, Bin / Cheng, Wei / Goswami, Prashant et al. | IET | 2017

    Free access