Self-adapting prediction model for traffic flow status

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    Abstract

    The purpose of the study was to develop a method for making a self-adapting short-term prediction model for the flow status. The model was based on field-measured travel time data and self-organising maps. The test site was Ring Road I in the Helsinki metropolitan area. The forecasts were based on the outcomes of previous moments when the traffic situation was similar to the present. The forecast was set to the most common outcome in the cluster of these similar samples. The model was allowed to work online and its performance was studied. The proportion of correct forecasts was 93.8-96.3% over the entire trial period and 80.9-82.3% in congested conditions for the model in normal weather and road conditions. The average daily change in the proportion of correct forecasts was positive over the whole trial period: +0.3-0.4%. Two naïve comparison models were made. Both comparison models performed considerably poorer than the self-adapting model.
    Original languageEnglish
    Title of host publicationProceedings of 12th WCTR
    Subtitle of host publicationWorld Conference on Transportation Research
    Place of PublicationLisbon
    Publication statusPublished - 2010
    MoE publication typeA4 Article in a conference publication
    EventWorld Conference on Transportation Research, WCTR - Lissabon, Portugal
    Duration: 11 Jul 201015 Jul 2010

    Conference

    ConferenceWorld Conference on Transportation Research, WCTR
    CountryPortugal
    CityLissabon
    Period11/07/1015/07/10

    Fingerprint

    prediction
    road
    traffic
    travel time
    metropolitan area
    weather
    forecast
    comparison
    trial

    Keywords

    • prediction
    • traffic flow status
    • self-organising map

    Cite this

    Innamaa, S. (2010). Self-adapting prediction model for traffic flow status. In Proceedings of 12th WCTR: World Conference on Transportation Research [15] Lisbon.
    Innamaa, Satu. / Self-adapting prediction model for traffic flow status. Proceedings of 12th WCTR: World Conference on Transportation Research. Lisbon, 2010.
    @inproceedings{bb98aaef5b5d4feca9ea69d2623b6445,
    title = "Self-adapting prediction model for traffic flow status",
    abstract = "The purpose of the study was to develop a method for making a self-adapting short-term prediction model for the flow status. The model was based on field-measured travel time data and self-organising maps. The test site was Ring Road I in the Helsinki metropolitan area. The forecasts were based on the outcomes of previous moments when the traffic situation was similar to the present. The forecast was set to the most common outcome in the cluster of these similar samples. The model was allowed to work online and its performance was studied. The proportion of correct forecasts was 93.8-96.3{\%} over the entire trial period and 80.9-82.3{\%} in congested conditions for the model in normal weather and road conditions. The average daily change in the proportion of correct forecasts was positive over the whole trial period: +0.3-0.4{\%}. Two na{\"i}ve comparison models were made. Both comparison models performed considerably poorer than the self-adapting model.",
    keywords = "prediction, traffic flow status, self-organising map",
    author = "Satu Innamaa",
    year = "2010",
    language = "English",
    isbn = "978-9-8996-9860-4",
    booktitle = "Proceedings of 12th WCTR",

    }

    Innamaa, S 2010, Self-adapting prediction model for traffic flow status. in Proceedings of 12th WCTR: World Conference on Transportation Research., 15, Lisbon, World Conference on Transportation Research, WCTR, Lissabon, Portugal, 11/07/10.

    Self-adapting prediction model for traffic flow status. / Innamaa, Satu.

    Proceedings of 12th WCTR: World Conference on Transportation Research. Lisbon, 2010. 15.

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    TY - GEN

    T1 - Self-adapting prediction model for traffic flow status

    AU - Innamaa, Satu

    PY - 2010

    Y1 - 2010

    N2 - The purpose of the study was to develop a method for making a self-adapting short-term prediction model for the flow status. The model was based on field-measured travel time data and self-organising maps. The test site was Ring Road I in the Helsinki metropolitan area. The forecasts were based on the outcomes of previous moments when the traffic situation was similar to the present. The forecast was set to the most common outcome in the cluster of these similar samples. The model was allowed to work online and its performance was studied. The proportion of correct forecasts was 93.8-96.3% over the entire trial period and 80.9-82.3% in congested conditions for the model in normal weather and road conditions. The average daily change in the proportion of correct forecasts was positive over the whole trial period: +0.3-0.4%. Two naïve comparison models were made. Both comparison models performed considerably poorer than the self-adapting model.

    AB - The purpose of the study was to develop a method for making a self-adapting short-term prediction model for the flow status. The model was based on field-measured travel time data and self-organising maps. The test site was Ring Road I in the Helsinki metropolitan area. The forecasts were based on the outcomes of previous moments when the traffic situation was similar to the present. The forecast was set to the most common outcome in the cluster of these similar samples. The model was allowed to work online and its performance was studied. The proportion of correct forecasts was 93.8-96.3% over the entire trial period and 80.9-82.3% in congested conditions for the model in normal weather and road conditions. The average daily change in the proportion of correct forecasts was positive over the whole trial period: +0.3-0.4%. Two naïve comparison models were made. Both comparison models performed considerably poorer than the self-adapting model.

    KW - prediction

    KW - traffic flow status

    KW - self-organising map

    M3 - Conference article in proceedings

    SN - 978-9-8996-9860-4

    BT - Proceedings of 12th WCTR

    CY - Lisbon

    ER -

    Innamaa S. Self-adapting prediction model for traffic flow status. In Proceedings of 12th WCTR: World Conference on Transportation Research. Lisbon. 2010. 15