3D CNN-based Accurate Prediction for Large-scale Traffic Flow

Yu, Feng; Wei, Dan; Zhang, Shuting; Shao, Yanli

doi:10.1109/icite.2019.8880210

Cited by 20 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Residual networks can increase the model depth to capture characters with longer distances and more complex structures. Yu [42] designed a three-dimensional CNN network to achieve large-scale prediction on traffic flow. To capture the spatio-temporal dependency, scholars exploit RNNs in combination with CNN-based networks for passenger flow prediction.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

A Hybrid GLM Model for Predicting Citywide Spatio-Temporal Metro Passenger Flow

Han

Peng

Wang³

et al. 2021

IJGI

View full text Add to dashboard Cite

Accurate prediction of citywide short-term metro passenger flow is essential to urban management and transport scheduling. Recently, an increasing number of researchers have applied deep learning models to passenger flow prediction. Nevertheless, the task is still challenging due to the complex spatial dependency on the metro network and the time-varying traffic patterns. Therefore, we propose a novel deep learning architecture combining graph attention networks (GAT) with long short-term memory (LSTM) networks, which is called the hybrid GLM (hybrid GAT and LSTM Model). The proposed model captures the spatial dependency via the graph attention layers and learns the temporal dependency via the LSTM layers. Moreover, some external factors are embedded. We tested the hybrid GLM by predicting the metro passenger flow in Shanghai, China. The results are compared with the forecasts from some typical data-driven models. The hybrid GLM gets the smallest root-mean-square error (RMSE) and mean absolute percentage error (MAPE) in different time intervals (TIs), which exhibits the superiority of the proposed model. In particular, in the TI 10 min, the hybrid GLM brings about 6–30% extra improvements in terms of RMSE. We additionally explore the sensitivity of the model to its parameters, which will aid the application of this model.

show abstract

Section: Deep Learning Methodsmentioning

confidence: 99%

A Hybrid GLM Model for Predicting Citywide Spatio-Temporal Metro Passenger Flow

Han

Peng

Wang³

et al. 2021

IJGI

View full text Add to dashboard Cite

show abstract

“…When it comes to the spatial models, the convolution operation is usually applied to generalize and analyze the spatial correlations among nearby locations or road sections. CNN is firstly used in traffic flow prediction to analyze several nearby locations' mutual influences in a transportation network [47]. Because CNN cannot efficiently analyze Non-Euclidean structure data , GCN is then introduced into traffic prediction to deal with graph-structured data, such as a transportation network composed of various road section nodes [6].…”

Section: Traffic Prediction Using Single Deep Learning Modelmentioning

confidence: 99%

A spatial-temporal short-term traffic flow prediction model based on dynamical-learning graph convolution mechanism

Chen¹,

Lü²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Short-term traffic flow prediction is a vital branch of the Intelligent Traffic System (ITS) and plays an important role in traffic management. Graph convolution network (GCN) is widely used in traffic prediction models to better deal with the graphical structure data of road networks. However, the influence weights among different road sections are usually distinct in real life, and hard to be manually analyzed. Traditional GCN mechanism, relying on manually-set adjacency matrix, is unable to dynamically learn such spatial pattern during the training. To deal with this drawback, this paper proposes a novel location graph convolutional network (Location-GCN). Location-GCN solves this problem by adding a new learnable matrix into the GCN mechanism, using the absolute value of this matrix to represent the distinct influence levels among different nodes. Then, long short-term memory (LSTM) is employed in the proposed traffic prediction model. Moreover, Trigonometric function encoding is used in this study to enable the short-term input sequence to convey the long-term periodical information. Ultimately, the proposed model is compared with the baseline models and evaluated on two real word traffic flow datasets. The results show our model is more accurate and robust on both datasets than other representative traffic prediction models.

show abstract

“…Ji, Xu, Yang, and Yu (2013) applied the 3D CNN model for human action recognition. Recently, 3D CNN was utilized for citywide traffic flow prediction (F. Yu, Wei, Zhang, & Shao, 2019) and taxi demand prediction (Kuang, Yan, Tan, Li, & Yang, 2019). Compared to 2D CNN, the 3D convolution kernel provides a simple and effective way to extract spatial-temporal features within such images simultaneously.…”

Section: Literature Reviewmentioning

confidence: 99%

Network‐wide traffic speed forecasting: 3D convolutional neural network with ensemble empirical mode decomposition

Zhang

Zhou

Chen

et al. 2020

Computer aided Civil Eng

View full text Add to dashboard Cite

Accurate traffic speed forecasting is one of the most critical tasks in proactive traffic management and the deployment of advanced traveler information systems. This paper proposes a hybrid forecasting approach named DeepEnsemble by integrating the three‐dimensional convolutional neural network (3D CNN) with ensemble empirical mode decomposition (EEMD). There are four steps in this hybrid approach. First, EEMD is adopted to decompose the complex traffic speed time series data with noise into several intrinsic mode functions (IMFs) and a residue. Second, a three‐dimensional tensor is established and fed into 3D CNN for prediction. Third, the output of 3D CNN prediction is obtained by a linear combination of the results of all components. Finally, the 3D CNN prediction output, external features, and historical features are fused to predict the network‐wide traffic speed simultaneously. The proposed DeepEnsemble approach is tested on the three‐month traffic speed series data of a real‐world large‐scale urban expressway network with 308 traffic flow detectors in Beijing, China. The experimental results indicate that DeepEnsemble outperforms the state‐of‐the‐art network‐wide traffic speed forecasting models. 3D CNN learns temporal, spatial, and depth information better than 2D CNN. Moreover, forecasting accuracy can be improved by employing EEMD. DeepEnsemble is a promising model with scalability and portability for network‐wide traffic speed prediction and can be further extended to conduct traffic status monitoring and congestion mitigation strategies.

show abstract

3D CNN-based Accurate Prediction for Large-scale Traffic Flow

Cited by 20 publications

References 11 publications

A Hybrid GLM Model for Predicting Citywide Spatio-Temporal Metro Passenger Flow

A Hybrid GLM Model for Predicting Citywide Spatio-Temporal Metro Passenger Flow

A spatial-temporal short-term traffic flow prediction model based on dynamical-learning graph convolution mechanism

Network‐wide traffic speed forecasting: 3D convolutional neural network with ensemble empirical mode decomposition

Contact Info

Product

Resources

About