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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multistep traffic forecasting on road networks is a crucial task insuccessful intelligent transportation system applications. To capture thecomplex non-stationary temporal dynamics and spatial dependency in multisteptraffic-condition prediction, we propose a novel deep learning framework namedattention graph convolutional sequence-to-sequence model (AGC-Seq2Seq). In theproposed deep learning framework, spatial and temporal dependencies are modeledthrough the Seq2Seq model and graph convolution network separately, and theattention mechanism along with a newly designed training method based on theSeq2Seq architecture is proposed to overcome the difficulty in multistepprediction and further capture the temporal heterogeneity of traffic pattern.We conduct numerical tests to compare AGC-Seq2Seq with other benchmark modelsusing a real-world dataset. The results indicate that our model yields the bestprediction performance in terms of various prediction error measures.Furthermore, the variation of spatiotemporal correlation of traffic conditionsunder different perdition steps and road segments is revealed throughsensitivity analyses.

Multistep Speed Prediction on Traffic Networks: A Graph Convolutional Sequence-to-Sequence Learning Approach with Attention Mechanism