Automated Dilated Spatio-Temporal Synchronous Graph Modeling for Traffic Prediction

Jin, Guangyin; Li, Fuxian; Zhang, Jinlei; Wang, Mudan; Huang, Jincai

doi:10.1109/tits.2022.3195232

Cited by 19 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 6) STGCN: 20 The spatiotemporal graph convolutional network (STGCN) mainly exploits the spatiotemporal dependencies of traffic states by employing both spatial graph convolution and temporal gated convolution. (7) Auto-DSTSGN: 46 This is a traffic spatial-temporal estimation model that consists of multiple automated dilated spatial-temporal synchronous graph (Auto-DSTSG) modules in a stacked form to capture complex spatial-temporal dependencies. (8) CorrSTN: 47 The correlation spatial-temporal network exploits features of different time periods to mining the correlation between traffic data.…”

Section: Comparison Of Estimation Resultsmentioning

confidence: 99%

“…It is a very popular model in traffic estimating and is widely used. LSTM: 32 The LSTM network is a commonly used method in time series modeling that has many successful applications in traffic state estimation. The settings of LSTM are the same as the parameters of the temporal feature block in this paper. STGCN: 20 The spatiotemporal graph convolutional network (STGCN) mainly exploits the spatiotemporal dependencies of traffic states by employing both spatial graph convolution and temporal gated convolution. Auto‐DSTSGN: 46 This is a traffic spatial‐temporal estimation model that consists of multiple automated dilated spatial‐temporal synchronous graph (Auto‐DSTSG) modules in a stacked form to capture complex spatial‐temporal dependencies. CorrSTN: 47 The correlation spatial‐temporal network exploits features of different time periods to mining the correlation between traffic data. And it takes advantage of an encoding‐decoding architecture to fully capture both spatial and temporal information.…”

Section: Methodsmentioning

confidence: 99%

“…Auto‐DSTSGN: 46 This is a traffic spatial‐temporal estimation model that consists of multiple automated dilated spatial‐temporal synchronous graph (Auto‐DSTSG) modules in a stacked form to capture complex spatial‐temporal dependencies.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Reducing hysteresis and over‐smoothing in traffic estimation: A multistream spatial‐temporal graph convolutional network

Liu

Zhao

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Accurate traffic estimation contributes to safer route planning for Autonomous Vehicles (AVs). Currently, deep learning methods based on graph convolution networks (GCNs) and recurrent neural networks (RNNs) are widely used in traffic estimation. However, such methods suffer from spatial over‐smoothing and temporal hysteresis, which lead to estimation results deviating from the ground truth. Therefore, a multistream spatial‐temporal graph convolutional network (MSGCN) is proposed in this paper to deal with these issues. It integrates local, global and differential spatial‐temporal features which are modeled from multiple dimensions to deal with spatially correlation and time‐varying evolution of traffic states. Experimental results obtained on a real‐world dataset demonstrate the effectiveness of the proposed MSGCN. Furthermore, we measure the performance in both usual and unusual traffic states. Compared to baseline models, MSGCN is more accurate and robust in the two states.

show abstract

Section: Comparison Of Estimation Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Reducing hysteresis and over‐smoothing in traffic estimation: A multistream spatial‐temporal graph convolutional network

Liu

Zhao

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…Some studies employ convolutional neural network (CNN) instead of RNN to learn temporal dynamics ( Wen et al, 2023 ; Ni & Zhang, 2022 ). To synchronize the extraction of spatial-temporal features, some work has designed graph structures that contain both spatial and temporal attributes ( Song et al, 2020 ; Li & Zhu, 2021 ; Jin et al, 2022 ; Wei et al, 2023 ). In spite of the pioneering advances in these studies, there is still a lack of sufficiently practical approaches in spatial and temporal synchronous learning owing to the complexity of traffic dynamics.…”

Section: Introductionmentioning

confidence: 99%

Dynamic multiple-graph spatial-temporal synchronous aggregation framework for traffic prediction in intelligent transportation systems

Yu,

Bao,

Shi

2024

PeerJ Computer Science

View full text Add to dashboard Cite

Accurate traffic prediction contributes significantly to the success of intelligent transportation systems (ITS), which enables ITS to rationally deploy road resources and enhance the utilization efficiency of road networks. Improvements in prediction performance are evident by utilizing synchronized rather than stepwise components to model spatial-temporal correlations. Some existing studies have designed graph structures containing spatial and temporal attributes to achieve spatial-temporal synchronous learning. However, two challenges remain due to the intricate dynamics: (a) Accounting for the impact of external factors in spatial-temporal synchronous modeling. (b) Multiple perspectives in constructing spatial-temporal synchronous graphs. To address the mentioned limitations, a novel model named dynamic multiple-graph spatial-temporal synchronous aggregation framework (DMSTSAF) for traffic prediction is proposed. Specifically, DMSTSAF utilizes a feature augmentation module (FAM) to adaptively incorporate traffic data with external factors and generate fused features as inputs to subsequent modules. Moreover, DMSTSAF introduces diverse spatial and temporal graphs according to different spatial-temporal relationships. Based on this, two types of spatial-temporal synchronous graphs and the corresponding synchronous aggregation modules are designed to simultaneously extract hidden features from various aspects. Extensive experiments constructed on four real-world datasets indicate that our model improves by 3.68–8.54% compared to the state-of-the-art baseline.

show abstract

“…There are at least two disadvantages in predicting congestion event: 1) The traditional traffic prediction framework only model dense variables on the road such as speed, not sparse ones such as congestion events. 2) Most traditional traffic prediction framework (Jin et al 2022;Yu, Yin, and Zhu 2018;Wu et al 2019;Jin et al 2020;Fang et al 2021;Song et al 2020;Li and Zhu 2021;Wang, Zhang, and Tsui 2021;Jin et al 2021) can only support the prediction in the given future time window (e.g., the next one hour), which is difficult to flexibly predict congestion occurring in arbitrary time intervals.…”

Section: Introductionmentioning

confidence: 99%

Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction

Jin

Liu

et al. 2023

AAAI

Self Cite

View full text Add to dashboard Cite

Traffic congestion event prediction is an important yet challenging task in intelligent transportation systems. Many existing works about traffic prediction integrate various temporal encoders and graph convolution networks (GCNs), called spatio-temporal graph-based neural networks, which focus on predicting dense variables such as flow, speed and demand in time snapshots, but they can hardly forecast the traffic congestion events that are sparsely distributed on the continuous time axis. In recent years, neural point process (NPP) has emerged as an appropriate framework for event prediction in continuous time scenarios. However, most conventional works about NPP cannot model the complex spatio-temporal dependencies and congestion evolution patterns. To address these limitations, we propose a spatio-temporal graph neural point process framework, named STGNPP for traffic congestion event prediction. Specifically, we first design the spatio-temporal graph learning module to fully capture the long-range spatio-temporal dependencies from the historical traffic state data along with the road network. The extracted spatio-temporal hidden representation and congestion event information are then fed into a continuous gated recurrent unit to model the congestion evolution patterns. In particular, to fully exploit the periodic information, we also improve the intensity function calculation of the point process with a periodic gated mechanism. Finally, our model simultaneously predicts the occurrence time and duration of the next congestion. Extensive experiments on two real-world datasets demonstrate that our method achieves superior performance in comparison to existing state-of-the-art approaches.

show abstract

Automated Dilated Spatio-Temporal Synchronous Graph Modeling for Traffic Prediction

Cited by 19 publications

References 35 publications

Reducing hysteresis and over‐smoothing in traffic estimation: A multistream spatial‐temporal graph convolutional network

Reducing hysteresis and over‐smoothing in traffic estimation: A multistream spatial‐temporal graph convolutional network

Dynamic multiple-graph spatial-temporal synchronous aggregation framework for traffic prediction in intelligent transportation systems

Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction

Contact Info

Product

Resources

About