With the continuous increase in the number of vehicles, severe traffic jams have become an increasingly common problem, which will directly affect the time consumed and money spent of the transport users. Predicting future traffic flow can help alleviate this problem to a certain extent. In this work, we firstly preprocess the data via selenium, OSS, and Message Queue and model the traffic flow using three machine learning algorithms, including Linear regression, Decision Tree, and Support Vector Machine. Then, we analyze the actual traffic data of Beijing on the Baidu map. This work shows that the accuracy of Random Forest is 0.719, which is the highest in these three methods. And the second is Logistic Regression and SVM.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Traffic Flow Prediction Using Machine Learning Methods


    Contributors:
    Wang, Hainan (author) / Wei, Xuetong (author) / Yao, Junyuan (author) / Zhang, Yue (author)


    Publication date :

    2021-12-01


    Size :

    3973730 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Traffic Flow Breakdown Prediction using Machine Learning Approaches

    Filipovska, Monika / Mahmassani, Hani S. | Transportation Research Record | 2020


    Prediction of Traffic Flow Propagation Using Machine Learning Algorithms

    Priya, Shristi / Singh, Divyashu / Sharma, Harshit et al. | IEEE | 2022


    Traffic Prediction Using Machine Learning

    Deekshetha, H. R. / Shreyas Madhav, A. V. / Tyagi, Amit Kumar | Springer Verlag | 2022


    Twitter-informed Prediction for Urban Traffic Flow Using Machine Learning

    Shoaeinaeini, Maryam / Ozturk, Oktay / Gupta, Deepak | IEEE | 2022


    Traffic Flow Prediction For Intelligent Transportation System Using Machine Learning

    Manikandan B.V. / Nathan T.R. / Naresh R. et al. | DOAJ | 2023

    Free access