Graph convolutional network approach applied to predict hourly bike-sharing demands considering spatial, temporal, and global effects

Kim, Tae San; Lee, Won Kyung; Sohn, So Young

doi:10.1371/journal.pone.0220782

Cited by 29 publications

(22 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A spatial adjacency matrix is usually distance-based. 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.…”

Section: B Adjacency Matricesmentioning

confidence: 99%

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

Chen

O’Connor

et al. 2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

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 an 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. Recently, convolutional neural networks (CNN) have been applied to extract the relationship between adjacent traffic networks whilst the recurrent neural networks (RNN) were used to arrest the temporal information. For short-term traffic prediction, fully connected long short-term memory (LSTM) [3] and CLTFP [4], two architectures mixed the long shortterm memory networks with convolutional operation, were

show abstract

Section: B Adjacency Matricesmentioning

confidence: 99%

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

Chen

O’Connor

et al. 2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

show abstract

“…However, when used to predict bike-sharing at the station level, CNN can only reflect inter-station relationship by geographical distance [39]. Some researchers attempted to apply deep learning architecture to graph data structure [39][40][41][42]. Taking bike stations as nodes, the bike-sharing network can be represented in a graph.…”

Section: A Short-term Bike-sharing Demand Predictionmentioning

confidence: 99%

“…Some researchers describe bike riding relationships in the complex heterogeneous spatial-temporal graph and used graph convolutional neural network (GCN) to capture non-Euclidean structures. Kim et al [39] constructed a GCN prediction model to predict hourly bike-sharing demand at the station level by incorporating spatial characteristics, temporal patterns, and global variables (weather and weekday/weekend). Yoshida et al [40] proposed a relational graph convolutional networkbased method to predict the demand at the station level.…”

Section: A Short-term Bike-sharing Demand Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Station Importance Evaluation in Dynamic Bike-Sharing Rebalancing Optimization Using an Entropy-Based TOPSIS Approach

Jin

2021

IEEE Access

View full text Add to dashboard Cite

As an eco-friendly travel mode, bike-sharing has prevailed around the world. However, the systems are imbalanced due to the asymmetric spatial and temporal distribution of user demand. Station prioritization strategies are needed to rebalance more shared bikes for more important stations. This paper proposes an evaluation method of station importance in dynamic bike-sharing rebalancing. Firstly, a shortterm demand prediction model is applied to capture the temporal and spatial characteristics of bike-sharing trip data and predict bike-sharing demand at the station level. Based on the prediction results, the method of determining rebalancing quantity is proposed with consideration of bike-sharing usage throughout the rebalancing period. Then, three criteria are employed to evaluate the importance of bike-sharing stations, including rebalancing quantity, closeness to inventory threshold, and distance from the key station. An entropy-based Technique for Order of Preference by Similarity to the Ideal Solution (TOPSIS) approach is proposed to weigh different criteria and evaluate station importance. Furthermore, the experiments on bikesharing data from Nanjing City demonstrate the effectiveness of the proposed methods. This research is helpful for operators and managers to dynamically rebalance shared bikes with high efficiency and improve the service quality of bike-sharing systems.

show abstract

“…Zhao et al [48] proposed a temporary graph revolutionary network, which combines GCN and Gated Recurrent Unit(GRU) to predict traffic information. Kim et al [36] considered the spatial and temporal influence, and the influence of global variables, such as weather and weekday/weekend to reflect non-stationlevel changes. And then used graph convolutional network to predict bike demands.…”

Section: B Graph Convolutional Network For Temporal Predictionmentioning

confidence: 99%

Joint Spatial and Temporal Modeling for Hydrological Prediction

et al. 2020

View full text Add to dashboard Cite

The accurate and timely estimation of river discharge plays an important role in hydrological modeling, especially for avoiding the consequences of flood events. The majority of existing work on hydrologic prediction focuses on modeling the inherent physical process for specific river basins, while the geographic-connections between rivers are largely ignored. Geographically connected rivers provide rich spatial information that can be used to predict discharge amounts. In this paper, we study a novel problem of exploiting both temporal patterns and spatial connections for hydrological prediction. We construct three relationship graphs for hydrological gauges in the study area: the hydraulic distance graph, the Euclidean distance graph and the correlation graph. We fuse these graphs into one hydrological network graph, and propose a novel framework ST-Hydro which exploits Graph Convolutional Networks (GCN) for learning the spatial feature representations, and Recurrent Neural Networks with carefully designed activation functions for capturing temporal features simultaneously for hydrological prediction. Experimental results on real world data set demonstrate that the proposed framework can predict the river discharge effectively and at an early stage. INDEX TERMS Hydrologic prediction, spatial and temporal modeling, graph convolutional networks.

show abstract

Graph convolutional network approach applied to predict hourly bike-sharing demands considering spatial, temporal, and global effects

Cited by 29 publications

References 29 publications

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

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

Station Importance Evaluation in Dynamic Bike-Sharing Rebalancing Optimization Using an Entropy-Based TOPSIS Approach

Joint Spatial and Temporal Modeling for Hydrological Prediction

Contact Info

Product

Resources

About