Research on Traffic Congestion Forecast Based on Deep Learning
In recent years, the rapid economic development of China, the increase of the urban population, the continuous growth of private car ownership, the uneven distribution of traffic flow, and the local congestion of the road network have caused traffic congestion. Traffic congestion has become an inevi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/2/108 |
| _version_ | 1827757088956219392 |
|---|---|
| author | Yangyang Qi Zesheng Cheng |
| author_facet | Yangyang Qi Zesheng Cheng |
| author_sort | Yangyang Qi |
| collection | DOAJ |
| description | In recent years, the rapid economic development of China, the increase of the urban population, the continuous growth of private car ownership, the uneven distribution of traffic flow, and the local congestion of the road network have caused traffic congestion. Traffic congestion has become an inevitable problem in the process of urban development, bringing hazards and hidden dangers to citizens’ travel and urban development. The management of traffic congestion first lies in the accurate completion of the identification of road traffic status and the need to predict road congestion in the city, so as to improve the use rate of urban infrastructure road facilities and better alleviate road congestion. In this study, a deep spatial and temporal network model (DSGCN) for predicting traffic congestion status is proposed. First, our study divides the traffic network into grids, where each grid represents a different independent region. In this paper, the centroids of the grid regions are abstracted as nodes, and the dynamic correlations between the nodes are expressed in the form of adjacency matrix. Then, Graph Convolutional Neural Network is used to capture the spatial correlation between regions and a two-layer long and short-term feature model (DSTM) is used to capture the temporal correlation between regions. Finally, the DSGCN outperforms other baseline models and has higher accuracy for traffic congestion prediction as demonstrated by experiments on real PeMS datasets. |
| first_indexed | 2024-03-11T08:39:49Z |
| format | Article |
| id | doaj.art-7b0a03928c3f4e2098b0ac7106d2b0be |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-11T08:39:49Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-7b0a03928c3f4e2098b0ac7106d2b0be2023-11-16T21:12:26ZengMDPI AGInformation2078-24892023-02-0114210810.3390/info14020108Research on Traffic Congestion Forecast Based on Deep LearningYangyang Qi0Zesheng Cheng1College of Computer Science and Technology, Qingdao University, Qingdao 266071, ChinaInstitute of Ubiquitous Networks and Urban Computing, Qingdao University, Qingdao 266071, ChinaIn recent years, the rapid economic development of China, the increase of the urban population, the continuous growth of private car ownership, the uneven distribution of traffic flow, and the local congestion of the road network have caused traffic congestion. Traffic congestion has become an inevitable problem in the process of urban development, bringing hazards and hidden dangers to citizens’ travel and urban development. The management of traffic congestion first lies in the accurate completion of the identification of road traffic status and the need to predict road congestion in the city, so as to improve the use rate of urban infrastructure road facilities and better alleviate road congestion. In this study, a deep spatial and temporal network model (DSGCN) for predicting traffic congestion status is proposed. First, our study divides the traffic network into grids, where each grid represents a different independent region. In this paper, the centroids of the grid regions are abstracted as nodes, and the dynamic correlations between the nodes are expressed in the form of adjacency matrix. Then, Graph Convolutional Neural Network is used to capture the spatial correlation between regions and a two-layer long and short-term feature model (DSTM) is used to capture the temporal correlation between regions. Finally, the DSGCN outperforms other baseline models and has higher accuracy for traffic congestion prediction as demonstrated by experiments on real PeMS datasets.https://www.mdpi.com/2078-2489/14/2/108urban trafficdeep learninggraph convolutiontrajectory data |
| spellingShingle | Yangyang Qi Zesheng Cheng Research on Traffic Congestion Forecast Based on Deep Learning Information urban traffic deep learning graph convolution trajectory data |
| title | Research on Traffic Congestion Forecast Based on Deep Learning |
| title_full | Research on Traffic Congestion Forecast Based on Deep Learning |
| title_fullStr | Research on Traffic Congestion Forecast Based on Deep Learning |
| title_full_unstemmed | Research on Traffic Congestion Forecast Based on Deep Learning |
| title_short | Research on Traffic Congestion Forecast Based on Deep Learning |
| title_sort | research on traffic congestion forecast based on deep learning |
| topic | urban traffic deep learning graph convolution trajectory data |
| url | https://www.mdpi.com/2078-2489/14/2/108 |
| work_keys_str_mv | AT yangyangqi researchontrafficcongestionforecastbasedondeeplearning AT zeshengcheng researchontrafficcongestionforecastbasedondeeplearning |