STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting

Bai, Lei; Yao, Lina; Kanhere, Salil S.; Wang, Xianzhi; Sheng, Quan Z.

doi:10.48550/arxiv.1905.10069

Cited by 13 publications

(23 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In traffic demand prediction, the importance of each previous step to target demand is different, and this influence changes with time. For instance, a temporal attention mechanism [7] is able to add an importance score for each historical time step to measure the influence and this strategy can effectively improve the accuracy on prediction accuracy.…”

Section: A Existing Methodsmentioning

confidence: 99%

“…Euclidean distances between different stations (i.e., nodes in graph) [5] [13] or the natural geographical distance [14] are usually used as weights for its entries. A temporal adjacency matrix can be defined based on the similarity score [7] (i.e., Pearson correlation coefficient) between the temporal information (i.e., historical traffic demand sequence) of each pair of nodes/stations. To combine the benefits of both spatial and temporal features, an spatialtemporal embedding (ST embedding) can be generated for each node in a graph [15].…”

Section: B Adjacency Matricesmentioning

confidence: 99%

“…Based on this, we compare the performance of different methods, including our proposed model, in a similar experimental setting. Specifically, the following methods are compared: (a) HA 1 ; (b) XGBoost [21]; (c) FC-LSTM [22]; (d) DCRNN [23]; (e) ST-GCN [5]; (f) STG2Seq [7]; (g) GraphWaveNet [16] and (h) CCRCN [15].…”

Section: Baseline Algorithmsmentioning

confidence: 99%

“…• For the implementation of the adjacency matrix proposed in ST-GCN [5], the sigma is set to 0.2 and the eps is set to 0.368; • For the implementation of the adjacency matrix proposed in STG2Seq [7], the sigma is set to 0.05; • For the implementation of the adjacency matrix proposed in CCRCN [15], the dimension of station feature is set to 20 and the sigma is set to 1. • Other adjacency matrices do not need parameters to be set.…”

Section: E Adjacency Matrix Setupmentioning

confidence: 99%

“…Spatialtemporal convolutional blocks were introduced and applied repeatedly in this architecture, combining several graph convolutional layers [6] with sequential convolution in order to represent the spatial-temporal relations. Subsequent to this approach, STG2Seq [7], a sequence-to-sequence variant of STGCN, is proposed with more reference on historical data and an attention module, for multi-step passenger demand forecasting. However, there are still some important issues to be solved in the ST-GCN architecture.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Comparative Study of Using Spatial-Temporal Graph Convolutional Networks for Predicting Availability in Bike Sharing Schemes

Chen¹,

Wu²,

O’Connor³

et al. 2021

Preprint

View full text Add to dashboard Cite

Accurately forecasting transportation demand is crucial for efficient urban traffic guidance, control and management. One solution to enhance the level of prediction accuracy is to leverage graph convolutional networks (GCN), a neural network based modelling approach with the ability to process data contained in graph based structures. As a powerful extension of GCN, a spatial-temporal graph convolutional network (ST-GCN) aims to capture the relationship of data contained in the graphical nodes across both spatial and temporal dimensions, which presents a novel deep learning paradigm for the analysis of complex time-series data that also involves spatial information as present in transportation use cases. In this paper, we present an Attention-based ST-GCN (AST-GCN) for predicting the number of available bikes in bike-sharing systems in cities, where the attention-based mechanism is introduced to further improve the performance of a ST-GCN. Furthermore, we also discuss the impacts of different modelling methods of adjacency matrices on the proposed architecture. Our experimental results are presented using two real-world datasets, Dublinbikes and NYC-Citi Bike, to illustrate the efficacy of our proposed model which outperforms the majority of existing approaches.

show abstract

Section: A Existing Methodsmentioning

confidence: 99%