Spatial–Temporal Deep Tensor Neural Networks for Large-Scale Urban Network Speed Prediction

Zhou, Lingxiao; Zhang, Shuaichao; Yu, Jingru; Chen, Xiqun

doi:10.1109/tits.2019.2932038

Cited by 20 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A large number of machine learning-based models in short-term traffic prediction have been published over the last four decades, such as Neural Networks (NN) (Yasdi, 1999;Innamaa, 2000;Ishak et al, 2003;Zhang and Zhang, 2016;Pamuła, 2019;Zhou et al, 2020), Support Vector Regression (SVR) (Lippi et al, 2013;Guo et al, 2018), Random Forests and k-Nearest Neighbours (Habtemichael and Cetin, 2016;Guo et al, 2017a). The main advantages of machine learningbased prediction models are that these models are less complicated to implement in different contents and have more accurate prediction results.…”

Section: Short-term Traffic Prediction With Machine Learning Toolsmentioning

confidence: 99%

Transferability improvement in short-term traffic prediction using stacked LSTM network

Guo

Sivakumar

et al. 2021

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

Section: Short-term Traffic Prediction With Machine Learning Toolsmentioning

confidence: 99%

Transferability improvement in short-term traffic prediction using stacked LSTM network

Guo

Sivakumar

et al. 2021

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

“…• ST-DTNN (L. Zhou, Zhang, Yu, & Chen, 2019): By putting the top-k detectors related to the target detector on the spatial dimension, a three-dimensional tensor is constructed. 2D CNN was applied for the network traffic speed prediction.…”

Section: Measures Of Effectivenessmentioning

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

Self Cite

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

“…Further validation of the socio-cultural factors associated with the observed transition will help to identify clear impacts and to develop strategies to minimise the impact of land-use change on regional livelihoods. Zhou et al (2020), a new speed prediction method based on spatiotemporal depth tensor neural network (st-dtnn) for large-scale urban road network with mixed roads is proposed. At the same time, the spatiotemporal correlation of different road sections is considered to improve the prediction accuracy of the whole network.…”

Section: Introductionmentioning

confidence: 99%

Prediction method of construction land expansion speed of ecological city based on BP neural network

Niu

Zhou

2022

IJETM

View full text Add to dashboard Cite

In order to solve the problems of low accuracy and poor convergence of traditional urban construction land expansion speed prediction, a new method based on BP neural network for ecological city construction land expansion speed prediction is proposed. On the basis of driving forces state responses (DSR) research framework model, this paper analyses the main components of the driving mechanism model of urban construction land expansion, finds out the driving factors, and verifies the unit root of its time series, as well as causality verification and screening, to establish the driving mechanism model of urban construction land expansion. After preprocessing the data in the model, the BP neural network is constructed to predict the expansion speed of urban construction land. The experimental results show that the proposed method has better convergence and higher prediction accuracy, which provides a reference for related research.

show abstract

Spatial–Temporal Deep Tensor Neural Networks for Large-Scale Urban Network Speed Prediction

Cited by 20 publications

References 29 publications

Transferability improvement in short-term traffic prediction using stacked LSTM network

Transferability improvement in short-term traffic prediction using stacked LSTM network

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

Prediction method of construction land expansion speed of ecological city based on BP neural network

Contact Info

Product

Resources

About