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

We present a novel data-driven approach of learning traffic flow patterns ofa transportation network given that many instances of origin to destination(OD) travel demand and link flows of the network are available. Instead ofestimating traffic flow patterns assuming certain user behavior (e.g., userequilibrium or system optimal), here we explore the idea of learning those flowpatterns directly from the data. To implement this idea, we have formulated thetraffic-assignment problem as a data-driven learning problem and developed aneural network-based framework known as Graph Convolutional Neural Network(GCNN) to solve it. The proposed framework represents the transportationnetwork and OD demand in an efficient way and utilizes the diffusion process ofmultiple OD demands from nodes to links. We validate the solutions of the modelagainst analytical solutions generated from running static userequilibrium-based traffic assignments over Sioux Falls and East Massachusettsnetworks. The validation result shows that the implemented GCNN model can learnthe flow patterns very well with less than 2% mean absolute difference betweenthe actual and estimated link flows for both networks under varying congestedconditions. When the training of the model is complete, it can instantlydetermine the traffic flows of a large-scale network. Hence this approach canovercome the challenges of deploying traffic assignment models over large-scalenetworks and open new directions of research in data-driven network modeling.

Data-Driven Traffic Assignment: A Novel Approach for Learning Traffic Flow Patterns Using a Graph Convolutional Neural Network