Hierarchical Spatio–Temporal Graph Convolutional Networks and Transformer Network for Traffic Flow Forecasting

Huo, Guangyu; Zhang, Yong; Wang, Boyue; Gao, Junbin; Hu, Yongli; Yin, Baocai

doi:10.1109/tits.2023.3234512

Cited by 45 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep-learning passenger flow prediction models are mostly used for short-term passenger flow prediction. More representative models include LSTM [28,29], GRU [30,31], RNN [32], GCN [33][34][35], and other deep learning models. Wang et al [36] proposed a spatio-temporal hypergraph convolutional model for metro passenger flow prediction.…”

Section: Literature Reviewmentioning

confidence: 99%

SAD-ARGRU: A Metro Passenger Flow Prediction Model for Graph Residual Gated Recurrent Networks

Zhang,

Chen,

Zhang

et al. 2024

Mathematics

View full text Add to dashboard Cite

This paper proposes a graph residual gated recurrent network subway passenger flow prediction model considering the flat-peak characteristics, which firstly proposes the use of an adaptive density clustering method, which is capable of dynamically dividing the flat-peak time period of subway passenger flow. Secondly, this paper proposes graph residual gated recurrent network, which uses a graph convolutional network fused with a residual network and combined with a gated recurrent network, to simultaneously learn the temporal and spatial characteristics of passenger flow. Finally, this paper proposes to use the spatial attention mechanism to learn the spatial features around the subway stations, construct the spatial local feature components, and fully learn the spatial features around the stations to realize the local quantization of the spatial features around the subway stations. The experimental results show that the graph residual gated recurrent network considering the flat-peak characteristics can effectively improve the prediction performance of the model, and the method proposed in this paper has the highest prediction accuracy when compared with the traditional prediction model.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

SAD-ARGRU: A Metro Passenger Flow Prediction Model for Graph Residual Gated Recurrent Networks

Zhang,

Chen,

Zhang

et al. 2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…Huo et al developed a hierarchical traffic flow forecasting network by merging LTT and STGC to address limitations in previous GCN-based methods. Compared to previous work, this model captures both short-term and long-term temporal relations in traffic flow data, while mitigating the over-smoothing problem [15].…”

Section: Plos Onementioning

confidence: 99%

A novel hybrid framework based on temporal convolution network and transformer for network traffic prediction

Zhang,

Gong,

Liu

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Background Accurately predicting mobile network traffic can help mobile network operators allocate resources more rationally and can facilitate stable and fast network services to users. However, due to burstiness and uncertainty, it is difficult to accurately predict network traffic. Methodology Considering the spatio-temporal correlation of network traffic, we proposed a deep-learning model, Convolutional Block Attention Module (CBAM) Spatio-Temporal Convolution Network-Transformer, for time-series prediction based on a CBAM attention mechanism, a Temporal Convolutional Network (TCN), and Transformer with a sparse self-attention mechanism. The model can be used to extract the spatio-temporal features of network traffic for prediction. First, we used the improved TCN for spatial information and added the CBAM attention mechanism, which we named CSTCN. This model dealt with important temporal and spatial features in network traffic. Second, Transformer was used to extract spatio-temporal features based on the sparse self-attention mechanism. The experiments in comparison with the baseline showed that the above work helped significantly to improve the prediction accuracy. We conducted experiments on a real network traffic dataset in the city of Milan. Results The results showed that CSTCN-Transformer reduced the mean square error and the mean average error of prediction results by 65.16%, 64.97%, and 60.26%, and by 51.36%, 53.10%, and 38.24%, respectively, compared to CSTCN, a Long Short-Term Memory network, and Transformer on test sets, which justified the model design in this paper.

show abstract

“…Traditional convolutional networks are only applicable to extracting the local features of Euclidean data, whereas traffic flows are non-Euclidean data. A GCN extends the traditional convolution process to graph-structured data and learns the neighbor information of nodes and edges to process non-Euclidean data and capture the dynamic spatial features of non-Euclidean data [18]. Currently, GCNs are mainly categorized into two types of methods, as follows: null domain and spectral domain methods.…”

Section: Introductionmentioning

confidence: 99%

Traffic Flow Prediction Research Based on an Interactive Dynamic Spatial–Temporal Graph Convolutional Probabilistic Sparse Attention Mechanism (IDG-PSAtt)

Ding,

He,

Huang

et al. 2024

Atmosphere

View full text Add to dashboard Cite

Accurate traffic flow prediction is highly important for relieving road congestion. Due to the intricate spatial–temporal dependence of traffic flows, especially the hidden dynamic correlations among road nodes, and the dynamic spatial–temporal characteristics of traffic flows, a traffic flow prediction model based on an interactive dynamic spatial–temporal graph convolutional probabilistic sparse attention mechanism (IDG-PSAtt) is proposed. Specifically, the IDG-PSAtt model consists of an interactive dynamic graph convolutional network (IL-DGCN) with a spatial–temporal convolution (ST-Conv) block and a probabilistic sparse self-attention (ProbSSAtt) mechanism. The IL-DGCN divides the time series of a traffic flow into intervals and synchronously and interactively shares the captured dynamic spatiotemporal features. The ST-Conv block is utilized to capture the complex dynamic spatial–temporal characteristics of the traffic flow, and the ProbSSAtt block is utilized for medium-to-long-term forecasting. In addition, a dynamic GCN is generated by fusing adaptive and learnable adjacency matrices to learn the hidden dynamic associations among road network nodes. Experimental results demonstrate that the IDG-PSAtt model outperforms the baseline methods in terms of prediction accuracy. Specifically, on METR-LA, the mean absolute error (MAE) and root mean square error (RMSE) induced by IDG-PSAtt for a 60 min forecasting scenario are reduced by 0.75 and 1.31, respectively, compared to those of the state-of-the-art models. This traffic flow prediction improvement will lead to more precise estimates of the emissions produced by mobile sources, resulting in more accurate air quality forecasts. Consequently, this research will greatly support local environmental management efforts.

show abstract

Hierarchical Spatio–Temporal Graph Convolutional Networks and Transformer Network for Traffic Flow Forecasting

Cited by 45 publications

References 33 publications

SAD-ARGRU: A Metro Passenger Flow Prediction Model for Graph Residual Gated Recurrent Networks

SAD-ARGRU: A Metro Passenger Flow Prediction Model for Graph Residual Gated Recurrent Networks

A novel hybrid framework based on temporal convolution network and transformer for network traffic prediction

Traffic Flow Prediction Research Based on an Interactive Dynamic Spatial–Temporal Graph Convolutional Probabilistic Sparse Attention Mechanism (IDG-PSAtt)

Contact Info

Product

Resources

About