eduzhai > Applied Sciences > Engineering >

Automatic Detection of Major Freeway Congestion Events Using Wireless Traffic Sensor Data A Machine Learning Approach

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: Monitoring the dynamics of traffic in major corridors can provide invaluableinsight for traffic planning purposes. An important requirement for thismonitoring is the availability of methods to automatically detect major trafficevents and to annotate the abundance of travel data. This paper introduces amachine learning based approach for reliable detection and characterization ofhighway traffic congestion events from hundreds of hours of traffic speed data.Indeed, the proposed approach is a generic approach for detection of changes inany given time series, which is the wireless traffic sensor data in the presentstudy. The speed data is initially time-windowed by a ten-hour long slidingwindow and fed into three Neural Networks that are used to detect the existenceand duration of congestion events (slowdowns) in each window. The slidingwindow captures each slowdown event multiple times and results in increasedconfidence in congestion detection. The training and parameter tuning areperformed on 17,483 hours of data that includes 168 slowdown events. This datais collected and labeled as part of the ongoing probe data validation studiesat the Center for Advanced Transportation Technologies (CATT) at the Universityof Maryland. The Neural networks are carefully trained to reduce the chances ofover-fitting to the training data. The experimental results show that thisapproach is able to successfully detect most of the congestion events, whilesignificantly outperforming a heuristic rule-based approach. Moreover, theproposed approach is shown to be more accurate in estimation of the start-timeand end-time of the congestion events.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×