Feng Chen

TL;DR: A comparison of the prediction precisions obtained for time granularities of 10, 15, and 30 min indicates that prediction precision increases with increasing time granularity, and this study can provide subway operators with insight into short-term passenger flow forecasting by leveraging deep learning models.

TL;DR: This study can provide critical insights for subway operators to optimise urban rail transit operations and propose a deep-learning architecture called Conv-GCN that combines a graph convolutional network (GCN) and a three-dimensional Convolutional neural network (3D CNN) that yields the best performance.

TL;DR: A channel-wise attentive split–convolutional neural network (CAS-CNN) is proposed that contributes to the development of short-term OD flow prediction, and it also lays the foundations of real-time URT operation and management.

TL;DR: Results show that the prediction based on subway station clusters can not only avoid the complication of developing numerous models for each of the hundreds of stations, but also improve the prediction performance, which make it possible to predict short-term passenger flow on a network scale using limited dataset.

TL;DR: A methodology was formulated based on elasticity and exhaustive transit card data, and a network approach was proposed to assess the influence of distance-based fare increases on ridership and revenue, and demonstrated that smart card data have great potential with regard to fare change evaluation.