Spatio-Temporal Multi-Scale Convolutional Network for Traffic Forecasting

Liu, Qidong; Li, Tong; Zhu, Rui; Hou, Zhiqun; Zhang, Zehui; Chen, Maoyu; Yang, Bing

doi:10.1145/3456172.3456210

Cited by 4 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DCRNN [2]: Spatial features are captured using diffusion convolution, whose diffusion process is based on random wandering on the graph, and temporal features of the traffic flow are captured using recurrent neural networks.…”

Section: Benchmarking Methodsmentioning

confidence: 99%

“…Guo et al [25] further added the spatial and temporal attention mechanisms based on MCSTGCN to extract spatio-temporal features separately, improving the prediction performance of the model. Li et al [2] proposed a diffusion convolution recurrent neural network (DCRNN), which uses a bi-directional random wandering diffusion GCN to extract spatial dependencies. Wu et al [26] proposed multivariate time series forecasting networks (MTGNN), which utilize the intrinsic dependencies between multiple road segments for traffic forecasting.…”

Section: Traffic Flow Forecastingmentioning

confidence: 99%

“…Due to the excellent results shown by graph convolutional networks in spatio-temporal data pattern mining, they are widely used in traffic prediction problems. STGCN [1] and DCRNN [2] use the distance between realistic road network nodes (detector) to characterize the spatial correlations between road segments. STSGCN [3] constructs a local spatio-temporal graph by combining information between nodes at different times to characterize the spatio-temporal correlations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spatio‐temporal adaptive graph convolutional networks for traffic flow forecasting

Wei

Gao

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Accurate forecasting of traffic flow is crucial for intelligent traffic control and guidance. It is very challenging to forecast the traffic flow due to the high non‐linearity, complexity and dynamicity of the data. Most existing forecasting methods focus on designing complicated graph neural network architectures to capture the spatio‐temporal features of traffic data with the help of predefined graphs. However, traffic data exhibit a strong spatial dependency, which means that there are often complex correlations between nodes in a road network topology graph. Moreover, the spatial correlations of the road network change over time. To capture the properties of the road network topology graph, a novel spatio‐temporal adaptive graph convolutional networks model (STAGCN) based on deep learning is proposed. Utilize adaptive graph generation block to capture the static and dynamic structures of the traffic road network respectively, and they are integrated to construct an adaptive road network topology graph. Then the spatio‐temporal features of the traffic data are captured using spatio‐temporal convolution blocks. Experiments were conducted on publicly available traffic datasets for freeway traffic in California, USA, and the results showed that the prediction accuracy of the STAGCN model outperformed multiple baseline methods.

show abstract

Section: Benchmarking Methodsmentioning

confidence: 99%

Section: Traffic Flow Forecastingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatio‐temporal adaptive graph convolutional networks for traffic flow forecasting

Wei

Gao

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…In an alternative approach, the diffusion convolutional recurrent network (DCRNN) is proposed to improve the spatio-temporal modeling capabilities of spectral graph convolution. This model generalized the graph convolution approach to operate on both directed and undirected graphs (Li et al, 2018c). The key contribution of this work is the proposed diffusion convolution operation, which relates the traffic flow stream to a diffusion process and can effectively capture stochastic and noisy data trends.…”

Section: Gcnmentioning

confidence: 99%

Traffic prediction using artificial intelligence: Review of recent advances and emerging opportunities

Shaygan¹,

Meese²,

Li³

et al. 2022

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

“…Large volumes of spatio-temporal (ST) data (e.g., GPS samples, location-based video footages, and remote sensing data) are increasingly collected and studied in diverse domains, including human mobility [118,119], intelligent transportation [120,121], urban planning [122,123], epidemiology [124,125], as well as environmental and climate science [126,127]. While recent advances in Machine Learning (ML), especially Deep Learning (DL) see great benefits in leveraging big ST data to facilitate model training and inference, transforming the raw ST data into ML ingestible features, however, still faces major challenges.…”

Section: Introductionmentioning

confidence: 99%

Towards advanced distributed data processing: framework, optimization, and application

Liu

View full text Add to dashboard Cite

The surge in available big data has drawn significant interest in distributed processing methods capable of handling the ever-expanding data volume and increasing computational complexities efficiently and at scale. While existing distributed data processing frameworks, such as Apache Spark, have proven effective in various applications, there is still considerable room for improvement and exploration in this field. This thesis focuses on three key aspects of advancing distributed data processing using Apache Spark. First, a novel framework is introduced to extend Spark's capabilities, enabling the efficient processing of large-scale spatio-temporal data to better serve machine-learning applications. This framework not only achieves high efficiency but also provides a user-friendly interface. Second, a deep-learning-based optimization approach tailored to enhance the efficiency of Spark SQL execution is proposed. The end-to-end system integration of this approach leads to practical performance gains. Last, a distributed solution for the computational-intensive large-scale microscopic crowd simulation is designed and implemented aiming to improve the scalability and efficiency of such applications. These three works collectively expand the application of distributed computing and enhance efficiency through the implementation of state-of-the-art techniques.

show abstract

Spatio-Temporal Multi-Scale Convolutional Network for Traffic Forecasting

Cited by 4 publications

References 15 publications

Spatio‐temporal adaptive graph convolutional networks for traffic flow forecasting

Spatio‐temporal adaptive graph convolutional networks for traffic flow forecasting

Traffic prediction using artificial intelligence: Review of recent advances and emerging opportunities

Towards advanced distributed data processing: framework, optimization, and application

Contact Info

Product

Resources

About