eduzhai > Applied Sciences > Engineering >

Short-Term Traffic Forecasting Using High-Resolution Traffic Data

  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: This paper develops a data-driven toolkit for traffic forecasting usinghigh-resolution (a.k.a. event-based) traffic data. This is the raw dataobtained from fixed sensors in urban roads. Time series of such raw dataexhibit heavy fluctuations from one time step to the next (typically on theorder of 0.1-1 second). Short-term forecasts (10-30 seconds into the future) oftraffic conditions are critical for traffic operations applications (e.g.,adaptive signal control). But traffic forecasting tools in the literature dealpredominantly with 3-5 minute aggregated data, where the typical signal cycleis on the order of 2 minutes. This renders such forecasts useless at theoperations level. To this end, we model the traffic forecasting problem as amatrix completion problem, where the forecasting inputs are mapped to a higherdimensional space using kernels. The formulation allows us to capture bothnonlinear dependencies between forecasting inputs and outputs but also allowsus to capture dependencies among the inputs. These dependencies correspond tocorrelations between different locations in the network. We further employadaptive boosting to enhance the training accuracy and capture historicalpatterns in the data. The performance of the proposed methods is verified usinghigh-resolution data obtained from a real-world traffic network in Abu Dhabi,UAE. Our experimental results show that the proposed method outperforms otherstate-of-the-art algorithms.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×