Predicting road traffic in road networks is essential for alleviating congestion and enhancing traffic flow efficiency. This study presents a traffic volume prediction model trained using time-series data collected from loop detectors installed at three junctions in Istanbul, Turkey. The detectors record vehicle counts, providing the historical data used to train a residual LSTM model designed to forecast vehicle volumes 15 minutes into the future. The proposed model achieved an average mean absolute error of 0.26 across multiple loop detectors, demonstrating its effectiveness in accurately predicting short-term traffic volumes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Forecasting Road Traffic Volume Using Temporal-Only Time Series Models


    Contributors:


    Publication date :

    2025-03-17


    Size :

    1044341 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Time-series Multivariate Multistep Traffic Flow Forecasting using Temporal Fusion Transformers

    Arnob, Saadman Sakif / Shuvro, Ali Abir / Rahman, Saadman et al. | Springer Verlag | 2025


    Time-series Multivariate Multistep Traffic Flow Forecasting using Temporal Fusion Transformers

    Arnob, Saadman Sakif / Shuvro, Ali Abir / Rahman, Saadman et al. | Springer Verlag | 2025


    MLP for Spatio-Temporal Traffic Volume Forecasting

    Dimara, Asimina / Triantafyllidis, Dimitrios / Krinidis, Stelios et al. | IEEE | 2021


    Short-term forecasting of bicycle traffic using structural time series models

    Doorley, Ronan / Pakrashi, Vikram / Caulfield, Brian et al. | IEEE | 2014


    Short term traffic forecasting using time series methods

    Moorthy, C. K. / Ratcliffe, B. G. | Taylor & Francis Verlag | 1988