STHSGCN: Spatial-temporal heterogeneous and synchronous graph convolution network for traffic flow prediction

Yu, Xian; Bao, Yin-Xin; Shi, Quan

doi:10.1016/j.heliyon.2023.e19927

Cited by 4 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It needs to consider the potential impact of the current control plan on future traffic conditions, resulting in limited control effectiveness. On the other hand, most of these existing control methods adopt a single-machine computing environment, which cannot meet the real-time requirements of traffic optimization and control in the context of big data [23,24]. Similar to facial muscle movements forming different expressions, the spatiotemporal evolution of short-term traffic flow in the road network constitutes different forms of traffic.…”

Section: B Application Of Deep Learning In Traffic Flow Prediction 1)...mentioning

confidence: 99%

Construction of Short-Term Traffic Flow Prediction Model Based on IoT and Deep Learning Algorithms

Sun,

Dou

2024

IJACSA

View full text Add to dashboard Cite

On a global scale, traffic problems are an essential factor affecting urban operations, particularly challenging the frequent occurrence of traffic congestion and accidents. The solution to the problem requires real-time and accurate prediction of traffic flow. This article mainly explores the application of the Internet of Things and deep learning in traffic flow prediction, aiming to solve the problem where existing methods cannot meet the requirements of real-time and accuracy. IoT devices, such as road sensors and in-vehicle GPS devices, which provides rich information for traffic flow prediction. With the ability of deep learning, it can not only learn and abstract a large amount of complex traffic data but also handle traffic flow prediction tasks in various complex situations. During the model construction process, the complexity of the road network was fully considered, practical algorithms were designed to fuse multi-source data, and the structure of the model was optimized to meet the needs of real-time prediction. The experimental results show that the absolute error of the test results is generally less than 6km/h, which can better reflect the traffic speed of the road section in the future.

show abstract

Section: B Application Of Deep Learning In Traffic Flow Prediction 1)...mentioning

confidence: 99%

Construction of Short-Term Traffic Flow Prediction Model Based on IoT and Deep Learning Algorithms

Sun,

Dou

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Ref. [ 36 ] fully considered the spatiotemporal heterogeneity when performing traffic prediction tasks, and used a causal spatiotemporal synchronous graph convolutional network to mine spatiotemporal correlations, achieving the best prediction results. Ref.…”

Section: Introductionmentioning

confidence: 99%

A Dual-Stream Cross AGFormer-GPT Network for Traffic Flow Prediction Based on Large-Scale Road Sensor Data

Sun,

Shi,

Jia

et al. 2024

Sensors

View full text Add to dashboard Cite

Traffic flow prediction can provide important reference data for managers to maintain traffic order, and can also be based on personal travel plans for optimal route selection. On account of the development of sensors and data collection technology, large-scale road network historical data can be effectively used, but their high non-linearity makes it meaningful to establish effective prediction models. In this regard, this paper proposes a dual-stream cross AGFormer-GPT network with prompt engineering for traffic flow prediction, which integrates traffic occupancy and speed as two prompts into traffic flow in the form of cross-attention, and uniquely mines spatial correlation and temporal correlation information through the dual-stream cross structure, effectively combining the advantages of the adaptive graph neural network and large language model to improve prediction accuracy. The experimental results on two PeMS road network data sets have verified that the model has improved by about 1.2% in traffic prediction accuracy under different road networks.

show abstract

Hierarchical Dynamic Spatio-Temporal Graph Convolutional Networks with Self-Supervised Learning for Traffic Flow Forecasting

Wei,

Song,

Liu

et al. 2024

Inventions

View full text Add to dashboard Cite

It is crucial for both traffic management organisations and individual commuters to be able to forecast traffic flows accurately. Graph neural networks made great strides in this field owing to their exceptional capacity to capture spatial correlations. However, existing approaches predominantly focus on local geographic correlations, ignoring cross-region interdependencies in a global context, which is insufficient to extract comprehensive semantic relationships, thereby limiting prediction accuracy. Additionally, most GCN-based models rely on pre-defined graphs and unchanging adjacency matrices to reflect the spatial relationships among node features, neglecting the dynamics of spatio-temporal features and leading to challenges in capturing the complexity and dynamic spatial dependencies in traffic data. To tackle these issues, this paper puts forward a fresh approach: a new self-supervised dynamic spatio-temporal graph convolutional network (SDSC) for traffic flow forecasting. The proposed SDSC model is a hierarchically structured graph–neural architecture that is intended to augment the representation of dynamic traffic patterns through a self-supervised learning paradigm. Specifically, a dynamic graph is created using a combination of temporal, spatial, and traffic data; then, a regional graph is constructed based on geographic correlation using clustering to capture cross-regional interdependencies. In the feature learning module, spatio-temporal correlations in traffic data are subjected to recursive extraction using dynamic graph convolution facilitated by Recurrent Neural Networks (RNNs). Furthermore, self-supervised learning is embedded within the network training process as an auxiliary task, with the objective of enhancing the prediction task by optimising the mutual information of the learned features across the two graph networks. The superior performance of the proposed SDSC model in comparison with SOTA approaches was confirmed by comprehensive experiments conducted on real road datasets, PeMSD4 and PeMSD8. These findings validate the efficacy of dynamic graph modelling and self-supervision tasks in improving the precision of traffic flow prediction.

show abstract

STHSGCN: Spatial-temporal heterogeneous and synchronous graph convolution network for traffic flow prediction

Cited by 4 publications

References 44 publications

Construction of Short-Term Traffic Flow Prediction Model Based on IoT and Deep Learning Algorithms

Construction of Short-Term Traffic Flow Prediction Model Based on IoT and Deep Learning Algorithms

A Dual-Stream Cross AGFormer-GPT Network for Traffic Flow Prediction Based on Large-Scale Road Sensor Data

Hierarchical Dynamic Spatio-Temporal Graph Convolutional Networks with Self-Supervised Learning for Traffic Flow Forecasting

Contact Info

Product

Resources

About