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

With the rapid growth of traffic sensors deployed, a massive amount oftraffic flow data are collected, revealing the long-term evolution of trafficflows and the gradual expansion of traffic networks. How to accuratelyforecasting these traffic flow attracts the attention of researchers as it isof great significance for improving the efficiency of transportation systems.However, existing methods mainly focus on the spatial-temporal correlation ofstatic networks, leaving the problem of efficiently learning models on networkswith expansion and evolving patterns less studied. To tackle this problem, wepropose a Streaming Traffic Flow Forecasting Framework, TrafficStream, based onGraph Neural Networks (GNNs) and Continual Learning (CL), achieving accuratepredictions and high efficiency. Firstly, we design a traffic pattern fusionmethod, cleverly integrating the new patterns that emerged during the long-termperiod into the model. A JS-divergence-based algorithm is proposed to mine newtraffic patterns. Secondly, we introduce CL to consolidate the knowledgelearned previously and transfer them to the current model. Specifically, weadopt two strategies: historical data replay and parameter smoothing. Weconstruct a streaming traffic dataset to verify the efficiency andeffectiveness of our model. Extensive experiments demonstrate its excellentpotential to extract traffic patterns with high efficiency on long-termstreaming network scene. The source code is available athttps://github.com/AprLie/TrafficStream.

TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning