Short Term Prediction of Parking Area states Using Real Time Data and Machine Learning Techniques

Jesper C. Provoost, Luc J.J. Wismans, Sander J. van der Drift, Maurice van Keulen, Andreas Kamilaris

    Research output: Contribution to conferencePaperpeer-review

    80 Downloads (Pure)

    Abstract

    Public road authorities and private mobility service providers need information on and derived from the current and predicted traffic states to act upon the daily urban system and its spatial and temporal dynamics. In this research, a real-time parking area state (occupancy, in- and out-flux) prediction model (up to 60 minutes ahead) has been developed using publicly available historic and real-time data sources. Based on a case study in a real-life scenario in the city of Arnhem, a Neural Network-based approach outperforms a Random Forrest-based one on all assessed performance measures, although the differences are small. Both are outperforming a naïve, seasonal random walk model. Although the performance degrades with increasing the prediction horizon, the model shows a performance gain of over 150% at a prediction horizon of 60 minutes compared with the naïve model. Furthermore, it is shown that predicting the in- and out-flux is a far more difficult task (i.e. performance gains of 30%), which needs more training data, not based exclusively on occupancy rate. However, the performance of predicting in- and out-flux is less sensitive for the prediction horizon. In addition, it is shown that real-time information of current occupancy rate is the independent variable with the highest contribution to the performance, although time, traffic flow and weather variables also deliver a significant contribution. During real-time deployment, the model performs 3 times better than the naïve model on average. As a result, it can provide valuable information for proactive traffic management as well as mobility service providers.
    Original languageEnglish
    Number of pages20
    Publication statusAccepted/In press - 12 Jan 2020
    Event99th Transportation Research Board (TRB) Annual Meeting 2020 - Walter E. Washington Convention Center, Washington, United States
    Duration: 12 Jan 202016 Jan 2020
    Conference number: 99
    http://www.trb.org/AnnualMeeting/AnnualMeeting.aspx

    Conference

    Conference99th Transportation Research Board (TRB) Annual Meeting 2020
    Abbreviated titleTRB 2020
    CountryUnited States
    CityWashington
    Period12/01/2016/01/20
    Internet address

    Keywords

    • Smart parking
    • Machine learning
    • Public data
    • Real-time prediction

    Fingerprint

    Dive into the research topics of 'Short Term Prediction of Parking Area states Using Real Time Data and Machine Learning Techniques'. Together they form a unique fingerprint.

    Cite this