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

Short-term forecasting of passenger flow is critical for transit managementand crowd regulation. Spatial dependencies, temporal dependencies,inter-station correlations driven by other latent factors, and exogenousfactors bring challenges to the short-term forecasts of passenger flow of urbanrail transit networks. An innovative deep learning approach, Multi-GraphConvolutional-Recurrent Neural Network (MGC-RNN) is proposed to forecastpassenger flow in urban rail transit systems to incorporate these complexfactors. We propose to use multiple graphs to encode the spatial and otherheterogenous inter-station correlations. The temporal dynamics of theinter-station correlations are also modeled via the proposed multi-graphconvolutional-recurrent neural network structure. Inflow and outflow of allstations can be collectively predicted with multiple time steps ahead via asequence to sequence(seq2seq) architecture. The proposed method is applied tothe short-term forecasts of passenger flow in Shenzhen Metro, China. Theexperimental results show that MGC-RNN outperforms the benchmark algorithms interms of forecasting accuracy. Besides, it is found that the inter-stationdriven by network distance, network structure, and recent flow patterns aresignificant factors for passenger flow forecasting. Moreover, the architectureof LSTM-encoder-decoder can capture the temporal dependencies well. In general,the proposed framework could provide multiple views of passenger flow dynamicsfor fine prediction and exhibit a possibility for multi-source heterogeneousdata fusion in the spatiotemporal forecast tasks.

Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flow