A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network
Traffic state data are key to the proper operation of intelligent transportation systems (ITS). However, traffic detectors often receive environmental factors that cause missing values in the collected traffic state data. Therefore, aiming at the above problem, a method for imputing missing traffic...
| Main Authors: | , , , |
|---|---|
| 格式: | 文件 |
| 语言: | English |
| 出版: |
MDPI AG
2023-12-01
|
| 丛编: | Sensors |
| 主题: | |
| 在线阅读: | https://www.mdpi.com/1424-8220/23/23/9601 |
| _version_ | 1827591937005191168 |
|---|---|
| author | Chenchen Zhang Lei Zhou Xuemei Xiao Dongwei Xu |
| author_facet | Chenchen Zhang Lei Zhou Xuemei Xiao Dongwei Xu |
| author_sort | Chenchen Zhang |
| collection | DOAJ |
| description | Traffic state data are key to the proper operation of intelligent transportation systems (ITS). However, traffic detectors often receive environmental factors that cause missing values in the collected traffic state data. Therefore, aiming at the above problem, a method for imputing missing traffic state data based on a Diffusion Convolutional Neural Network–Generative Adversarial Network (DCNN-GAN) is proposed in this paper. The proposed method uses a graph embedding algorithm to construct a road network structure based on spatial correlation instead of the original road network structure; through the use of a GAN for confrontation training, it is possible to generate missing traffic state data based on the known data of the road network. In the generator, the spatiotemporal features of the reconstructed road network are extracted by the DCNN to realize the imputation. Two real traffic datasets were used to verify the effectiveness of this method, with the results of the proposed model proving better than those of the other models used for comparison. |
| first_indexed | 2024-03-09T01:41:40Z |
| format | Article |
| id | doaj.art-069cd4cb9ef0442eb2394d27d6ec1d3c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T01:41:40Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-069cd4cb9ef0442eb2394d27d6ec1d3c2023-12-08T15:26:33ZengMDPI AGSensors1424-82202023-12-012323960110.3390/s23239601A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial NetworkChenchen Zhang0Lei Zhou1Xuemei Xiao2Dongwei Xu3School of Mechanical and Automotive Engineering, Xiamen University of Technology, Xiamen 361024, ChinaInstitute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023, ChinaSchool of Mechanical and Automotive Engineering, Xiamen University of Technology, Xiamen 361024, ChinaInstitute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023, ChinaTraffic state data are key to the proper operation of intelligent transportation systems (ITS). However, traffic detectors often receive environmental factors that cause missing values in the collected traffic state data. Therefore, aiming at the above problem, a method for imputing missing traffic state data based on a Diffusion Convolutional Neural Network–Generative Adversarial Network (DCNN-GAN) is proposed in this paper. The proposed method uses a graph embedding algorithm to construct a road network structure based on spatial correlation instead of the original road network structure; through the use of a GAN for confrontation training, it is possible to generate missing traffic state data based on the known data of the road network. In the generator, the spatiotemporal features of the reconstructed road network are extracted by the DCNN to realize the imputation. Two real traffic datasets were used to verify the effectiveness of this method, with the results of the proposed model proving better than those of the other models used for comparison.https://www.mdpi.com/1424-8220/23/23/9601graph embeddingdeepwalkgenerative adversarial networkdiffusion convolutional neural networksdata imputation |
| spellingShingle | Chenchen Zhang Lei Zhou Xuemei Xiao Dongwei Xu A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network Sensors graph embedding deepwalk generative adversarial network diffusion convolutional neural networks data imputation |
| title | A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network |
| title_full | A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network |
| title_fullStr | A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network |
| title_full_unstemmed | A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network |
| title_short | A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network |
| title_sort | missing traffic data imputation method based on a diffusion convolutional neural network generative adversarial network |
| topic | graph embedding deepwalk generative adversarial network diffusion convolutional neural networks data imputation |
| url | https://www.mdpi.com/1424-8220/23/23/9601 |
| work_keys_str_mv | AT chenchenzhang amissingtrafficdataimputationmethodbasedonadiffusionconvolutionalneuralnetworkgenerativeadversarialnetwork AT leizhou amissingtrafficdataimputationmethodbasedonadiffusionconvolutionalneuralnetworkgenerativeadversarialnetwork AT xuemeixiao amissingtrafficdataimputationmethodbasedonadiffusionconvolutionalneuralnetworkgenerativeadversarialnetwork AT dongweixu amissingtrafficdataimputationmethodbasedonadiffusionconvolutionalneuralnetworkgenerativeadversarialnetwork AT chenchenzhang missingtrafficdataimputationmethodbasedonadiffusionconvolutionalneuralnetworkgenerativeadversarialnetwork AT leizhou missingtrafficdataimputationmethodbasedonadiffusionconvolutionalneuralnetworkgenerativeadversarialnetwork AT xuemeixiao missingtrafficdataimputationmethodbasedonadiffusionconvolutionalneuralnetworkgenerativeadversarialnetwork AT dongweixu missingtrafficdataimputationmethodbasedonadiffusionconvolutionalneuralnetworkgenerativeadversarialnetwork |