Missing values are an important issue for traffic data programs and lead to difficulties in data analyses and application. Previous research accurately imputed missing hourly volumes of a range from a few days up to one and a half weeks for various types of traffic counts. However, imputation errors of the applied hourly models increase dramatically after some reliable imputing periods; this indicates their limitations in real applications. Therefore, this study investigates pattern-matching algorithms to fill large missing data intervals. The algorithms use historical data to develop a series of candidate patterns and compare them to patterns with missing data. Data from the best-fit pattern is then used to estimate the missing data. The algorithms show improved accuracy over traditional models used in practice and prove suitable to impute missing hourly, daily, and monthly traffic volume data.


    Access

    Download

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Matching Hourly, Daily, and Monthly Traffic Patterns to Estimate Missing Volume Data


    Additional title:

    Transportation Research Record: Journal of the Transportation Research Board


    Contributors:


    Publication date :

    2006-01-01




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English