This paper addresses the long-standing challenge of traffic congestion in urban areas exacerbated by population growth and increased vehicular traffic. Accurate traffic flow prediction is crucial for the effective functioning of intelligent transportation systems (ITS) to control traffic and enhance safety. This study focused on exploring various hybrid deep learning models, including LSTM_ARIMA, LSTM_ XGB, and GRU_CNN. Among these, LSTM_ARIMA emerged as the most promising and consistently outperformed the other methods in terms of the prediction accuracy. Experiments conducted on real traffic data demonstrated a significant reduction in the root mean square error and an improvement in the R score when the LSTM_ARIMA model was utilized. The findings of this research contribute to the advancement of traffic prediction methods, with implications for urban planning, traffic optimization, and overall traffic safety enhancement.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Integrating Hybrid Deep Learning for Improving Traffic Flow Prediction


    Additional title:

    Lect. Notes in Networks, Syst.


    Contributors:

    Conference:

    International Conference on Smart Systems and Emerging Technologies ; 2024 ; Marrakech, Morocco November 19, 2024 - November 21, 2024



    Publication date :

    2025-08-14


    Size :

    10 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Traffic flow prediction method based on hybrid deep learning

    XIA DAWEN / CHEN YAN / LI HUAQING et al. | European Patent Office | 2023

    Free access


    Non-Stationary Traffic Flow Prediction Using Deep Learning

    Koesdwiady, Arief / Bedawi, Safaa / Ou, Chaojie et al. | IEEE | 2018


    Deep Learning for Short-Term Traffic Flow Prediction

    Polson, Nicholas | Online Contents | 2016


    Motorway Traffic Flow Prediction using Advanced Deep Learning

    Mihaita, Adriana-Simona / Li, Haowen / He, Zongyang et al. | IEEE | 2019