Road travel time prediction model based on improved spatiotemporal graph convolutional network

被引：0
|
作者：
Wang Z. [1 ]
Li P. [1 ]
Yang H. [2 ]
Wu B. [3 ]
机构：
[1] College of Transport and Communications, Shanghai Maritime University, Shanghai
[2] Faculty of Maritime and Transportation, Ningbo University, Ningbo
[3] Key Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai
来源：
Dongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Southeast University (Natural Science Edition) | 2024年 / 54卷 / 04期
关键词：
graph convolutional networks; spatiotemporal dependence; transportation engineering; travel time prediction; weather factors;
D O I：
10.3969/j.issn.1001-0505.2024.04.027
中图分类号：
学科分类号：
摘要：
To enhance the accuracy of travel time prediction in road networks,a spatiotemporal graph convolutional network model based on attribute enhancement and attention mechanisms was proposed considering spatial dependencies,temporal dependencies,and weather impact of travel time. First,an attribute enhancement unit was constructed to integrate travel time and weather information. Subsequently,spatial dependencies were captured using a graph convolutional network,and temporal dependencies were captured using gate-recurrent units. An attention mechanism was employed to enhance the model's learning of features. Finally,the model was utilized to predict future travel times at 15,30,45,and 60 min intervals on a real dataset. The results show that the root mean square error (RMSE)of the prediction results are 0. 045 3,0. 045 6,0. 045 7,and 0. 046 8,respectively,which are better than other models. When temporal,spatial,and weather factors are considered,a reduction of about 10. 3% in prediction error is observed compared with scenarios without weather consideration. Similarly,a reduction of about 24. 2% in prediction error is observed compared with scenarios without accounting for spatial dependency. It shows that the model can better describe the spatiotemporal dependence and the influence of external conditions. © 2024 Southeast University. All rights reserved.
引用
收藏
页码：1022 / 1029
页数：7
相关论文
共 28 条
  • [11] Tian F L, Wang Z X, Sun X Y, Et al., Combined prediction model of truck multi-section travel time in open-pit mine based on velocity field[J], Journal of Mine Automation, 48, 6, (2022)
  • [12] Kang L L, Hu G J, Huang H, Et al., Urban traffic travel time short-term prediction model based on spatiotemporal feature extraction[J], Journal of Advanced Transportation, 2020, (2020)
  • [13] Yuan Y A, Shao C F, Cao Z C, Et al., Bus dynamic travel time prediction:Using a deep feature extraction framework based on RNN and DNN[J], Electronics, 9, 11, (2020)
  • [14] Gunduz G, Acarman T., Vehicle travel time estimation using sequence prediction[J], Promet-Traffic &Transportation, 32, 1, (2020)
  • [15] Liu S, Peng Y, Shao Y M, Et al., Expressway travel time prediction based on gated recurrent unit neural networks [J ], Applied Mathematics and Mechanics, 40, 11, pp. 1289-1298, (2019)
  • [16] Zhang M, Li Y Y, Xie J J., Application of EA-GRU model in the prediction of urban traffic travel time[J], Journal of Nanjing University of Technology (Natural Science Edition), 44, 4, (2022)
  • [17] Ran X D, Shan Z G, Fang Y F, Et al., Travel time prediction by providing constraints on a convolutional neural network[J], IEEE Access, 6, (2018)
  • [18] Li X T, Quan W, Wang H, Et al., Route travel time prediction on deep learning model through spatiotemporal features[J], Journal of Jilin University (Engineering and Technology Edition), 52, 3, pp. 557-563, (2022)
  • [19] Shen Y B, Hua J X, Jin C Q, Et al., TCL:Tensor-CNN-LSTM for travel time prediction with sparse trajectory data[M], Database Systems for Advanced Applications, (2019)
  • [20] Wu J Q, Wu Q, Shen J, Et al., Towards attention-based convolutional long short-term memory for travel time prediction of bus journeys[J], Sensors, 20, 12, (2020)
123