The imputation of time series traffic flow data is of great significance to the intelligent transportation, urban planning, and road emergency handling. This paper proposes a filling missing time series traffic data with Generative Adversarial Network (ST-FVGAN), which not only considers the spatio-temporal correlation and utilizes the idea of data generating of the Generative Adversarial Network, but also considers the external factors and introduces a more comprehensive loss function. Specifically, the model firstly constructs a Generator network which is composed of convolutional layer, residual block, and pixelshuffle block for the better potential distribution of the existing data, and then use the Discriminator network for the input judging. Experiments are conducted on the open-source TaxiBJ GPS dataset, and evaluated by the root mean square error (RMSE) index. The experimental results show that our model has the better accurate and reasonable performance than the traditional imputation methods
ST-FVGAN: filling series traffic missing values with generative adversarial network
Transportation Letters ; 14 , 4 ; 407-415
2022-04-21
9 pages
Article (Journal)
Electronic Resource
Unknown
Missing traffic state data filling method based on generative adversarial network
European Patent Office | 2023
|Traffic flow prediction method based on generative adversarial network
European Patent Office | 2021
|