Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection
Abstract Traffic time series anomaly detection has been intensively studied for years because of its potential applications in intelligent transportation. However, classical traffic anomaly detection methods often overlook the evolving dynamic associations between road network nodes, which leads to...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-51374-3 |
| _version_ | 1797355702444883968 |
|---|---|
| author | Zhiyu Ren Xiaojie Li Jing Peng Ken Chen Qushan Tan Xi Wu Canghong Shi |
| author_facet | Zhiyu Ren Xiaojie Li Jing Peng Ken Chen Qushan Tan Xi Wu Canghong Shi |
| author_sort | Zhiyu Ren |
| collection | DOAJ |
| description | Abstract Traffic time series anomaly detection has been intensively studied for years because of its potential applications in intelligent transportation. However, classical traffic anomaly detection methods often overlook the evolving dynamic associations between road network nodes, which leads to challenges in capturing the long-term temporal correlations, spatial characteristics, and abnormal node behaviors in datasets with high periodicity and trends, such as morning peak travel periods. In this paper, we propose a mirror temporal graph autoencoder (MTGAE) framework to explore anomalies and capture unseen nodes and the spatiotemporal correlation between nodes in the traffic network. Specifically, we propose the mirror temporal convolutional module to enhance feature extraction capabilities and capture hidden node-to-node features in the traffic network. Morever, we propose the graph convolutional gate recurrent unit cell (GCGRU CELL) module. This module uses Gaussian kernel functions to map data into a high-dimensional space, and enables the identification of anomalous information and potential anomalies within the complex interdependencies of the traffic network, based on prior knowledge and input data. We compared our work with several other advanced deep-learning anomaly detection models. Experimental results on the NYC dataset illustrate that our model works best compared to other models for traffic anomaly detection. |
| first_indexed | 2024-03-08T14:15:54Z |
| format | Article |
| id | doaj.art-2e41df57b73e4ace8b3d4da03250a356 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-08T14:15:54Z |
| publishDate | 2024-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-2e41df57b73e4ace8b3d4da03250a3562024-01-14T12:23:59ZengNature PortfolioScientific Reports2045-23222024-01-0114111410.1038/s41598-024-51374-3Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detectionZhiyu Ren0Xiaojie Li1Jing Peng2Ken Chen3Qushan Tan4Xi Wu5Canghong Shi6The College of Computer Science Chengdu University of Information TechnologyThe College of Computer Science Chengdu University of Information TechnologyThe College of Computer Science Chengdu University of Information TechnologySichuan Digital Transportation Technology Co., LtdSichuan Digital Transportation Technology Co., LtdThe College of Computer Science Chengdu University of Information TechnologySchool of Computer and Software Engineering, Xihua UniversityAbstract Traffic time series anomaly detection has been intensively studied for years because of its potential applications in intelligent transportation. However, classical traffic anomaly detection methods often overlook the evolving dynamic associations between road network nodes, which leads to challenges in capturing the long-term temporal correlations, spatial characteristics, and abnormal node behaviors in datasets with high periodicity and trends, such as morning peak travel periods. In this paper, we propose a mirror temporal graph autoencoder (MTGAE) framework to explore anomalies and capture unseen nodes and the spatiotemporal correlation between nodes in the traffic network. Specifically, we propose the mirror temporal convolutional module to enhance feature extraction capabilities and capture hidden node-to-node features in the traffic network. Morever, we propose the graph convolutional gate recurrent unit cell (GCGRU CELL) module. This module uses Gaussian kernel functions to map data into a high-dimensional space, and enables the identification of anomalous information and potential anomalies within the complex interdependencies of the traffic network, based on prior knowledge and input data. We compared our work with several other advanced deep-learning anomaly detection models. Experimental results on the NYC dataset illustrate that our model works best compared to other models for traffic anomaly detection.https://doi.org/10.1038/s41598-024-51374-3 |
| spellingShingle | Zhiyu Ren Xiaojie Li Jing Peng Ken Chen Qushan Tan Xi Wu Canghong Shi Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection Scientific Reports |
| title | Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection |
| title_full | Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection |
| title_fullStr | Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection |
| title_full_unstemmed | Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection |
| title_short | Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection |
| title_sort | graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection |
| url | https://doi.org/10.1038/s41598-024-51374-3 |
| work_keys_str_mv | AT zhiyuren graphautoencoderwithmirrortemporalconvolutionalnetworksfortrafficanomalydetection AT xiaojieli graphautoencoderwithmirrortemporalconvolutionalnetworksfortrafficanomalydetection AT jingpeng graphautoencoderwithmirrortemporalconvolutionalnetworksfortrafficanomalydetection AT kenchen graphautoencoderwithmirrortemporalconvolutionalnetworksfortrafficanomalydetection AT qushantan graphautoencoderwithmirrortemporalconvolutionalnetworksfortrafficanomalydetection AT xiwu graphautoencoderwithmirrortemporalconvolutionalnetworksfortrafficanomalydetection AT canghongshi graphautoencoderwithmirrortemporalconvolutionalnetworksfortrafficanomalydetection |