Due to the increasing popularity of smartphones and in-dash navigation equipment, traffic data gathered by mobile devices has grown in popularity as a basis for predicting traffic conditions. Mobile devices submit location information to a central server, where future traffic conditions are computed. Because this type of system would be expensive to test with real drivers, algorithms for road traffic prediction are often evaluated according to the outcomes of simulations. These simulations frequently use the same types of vehicle data to model the flow of traffic. Based on the observation that these algorithm simulators share common functionality, we have developed a framework to facilitate the rapid development of simulators for traffic prediction. Using our framework, developers can quickly implement traffic prediction simulators with included data processing and visualization features. To date, we have utilized the framework in creating two separate simulators for influence-aware predictive density queries and naive density queries, respectively.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An extensible simulation framework for evaluating centralized traffic prediction algorithms


    Contributors:


    Publication date :

    2015-10-01


    Size :

    136702 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Centralized traffic control

    Engineering Index Backfile | 1931


    Centralized traffic control

    Rudd, A.H. | Engineering Index Backfile | 1932


    Centralized traffic control

    Kellenberger, K.E. | Engineering Index Backfile | 1932


    Centralized traffic control

    Engineering Index Backfile | 1931