Bus passenger flow prediction with a dynamic graph neural network and bidirectional gated recurrent unit

Xinyi Zhou

doi:10.1016/j.scs.2026.107766

Bus passenger flow prediction with a dynamic graph neural network and bidirectional gated recurrent unit

2026-08-04

0

PRE

AI

X

Xinyi Zhou *

N

Nizar Bouguila

Z

Zachary Patterson

DOI：10.1016/j.scs.2026.107766

Original

Original request for help

Save

Abstract

En 中文

• DGCN-BiGRU for short-term passenger flow prediction on dynamic transit networks. • Constructs daily dynamic bus graphs for stop/route cancellations and speed access. • Multi-source and branch temporal fusion with attention for heterogeneous flows. • Shows superior accuracy, disruption robustness and seasonal transfer on Ames/EXO.

Bus passenger flow prediction with a dynamic graph neural network and bidirectional gated recurrent unit

Abstract

Journal

Organization

Cited Papers

Citing Papers