English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Traffic volume is an indispensable ingredient to provide fine-grainedinformation for traffic management and control. However, due to limiteddeployment of traffic sensors, obtaining full-scale volume information is farfrom easy. Existing works on this topic primarily focus on improving theoverall estimation accuracy of a particular method and ignore the underlyingchallenges of volume estimation, thereby having inferior performances on somecritical tasks. This paper studies two key problems with regard to trafficvolume estimation: (1) underdetermined traffic flows caused by undetectedmovements, and (2) non-equilibrium traffic flows arise from congestionpropagation. Here we demonstrate a graph-based deep learning method that canoffer a data-driven, model-free and correlation adaptive approach to tackle theabove issues and perform accurate network-wide traffic volume estimation.Particularly, in order to quantify the dynamic and nonlinear relationshipsbetween traffic speed and volume for the estimation of underdetermined flows, aspeed patternadaptive adjacent matrix based on graph attention is developed andintegrated into the graph convolution process, to capture non-localcorrelations between sensors. To measure the impacts of non-equilibrium flows,a temporal masked and clipped attention combined with a gated temporalconvolution layer is customized to capture time-asynchronous correlationsbetween upstream and downstream sensors. We then evaluate our model on areal-world highway traffic volume dataset and compare it with several benchmarkmodels. It is demonstrated that the proposed model achieves high estimationaccuracy even under 20% sensor coverage rate and outperforms other baselinessignificantly, especially on underdetermined and non-equilibrium flowlocations. Furthermore, comprehensive quantitative model analysis are alsocarried out to justify the model designs.

Towards better traffic volume estimation: Jointly addressing the underdetermination and nonequilibrium problems with correlation-adaptive GNNs