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

Deep graph convolution networks (GCNs) have recently shown excellentperformance in traffic prediction tasks. However, they face some challenges.First, few existing models consider the influence of auxiliary information,i.e., weather and holidays, which may result in a poor grasp ofspatial-temporal dynamics of traffic data. Second, both the construction of adynamic adjacent matrix and regular graph convolution operations have quadraticcomputation complexity, which restricts the scalability of GCN-based models. Toaddress such challenges, this work proposes a deep encoder-decoder modelentitled AIMSAN. It contains an auxiliary information-aware module (AIM) andsparse cross attention-based graph convolution network (SAN). The former learnsmulti-attribute auxiliary information and obtains its embedded presentation ofdifferent time-window sizes. The latter uses a cross-attention mechanism toconstruct dynamic adjacent matrices by fusing traffic data and embeddedauxiliary data. Then, SAN applies diffusion GCN on traffic data to mine richspatial-temporal dynamics. Furthermore, AIMSAN considers and uses the spatialsparseness of traffic nodes to reduce the quadratic computation complexity.Experimental results on three public traffic datasets demonstrate that theproposed method outperforms other counterparts in terms of various performanceindices. Specifically, the proposed method has competitive performance with thestate-of-the-art algorithms but saves 35.74% of GPU memory usage, 42.25% oftraining time, and 45.51% of validation time on average.

A Sparse Cross Attention-based Graph Convolution Network with Auxiliary Information Awareness for Traffic Flow Prediction