A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Multicause Automatic Real-Time Identification of Urban Road Traffic Congestion Based on Bayesian Network
Urban road traffic congestion is caused by various factors, such as dynamic and real-time, complexity, and changeability, and existing methods are subjective, have low accuracy and poor real-time, and are unable to automatically identify. This study proposes a multicause automatic real-time identification of urban road traffic congestion on the basis of the Bayesian network. First, the method performs systematic mechanism analysis and simulation verification on the relationship between the dynamic observable variables of urban road traffic and the multiple congestion causes to construct the Bayesian network structure. Second, the obtained measured historical data are used for parameter learning and training to obtain the complete Bayesian network model. Finally, multiple causes of traffic congestion can be automatically and simultaneously identified in real time when inputting the observable variables of traffic under road working conditions into the Bayesian network model. This method has high flexibility that can help express the correlation of nodes better and has strong interpretability, which can fully use expert experience and knowledge and achieve automatization in real time. The results in the research on Quanxiu Street, Quanzhou City show that the construction of the multicause automatic real-time identification of urban road traffic congestion based on the Bayesian network is reasonable. Five congestion causes have higher recognition accuracy rates than contrast methods, which include pedestrian influence, peak traffic, parking occupied road, unreasonable signal timing, and impact of traffic crossing the road.
Multicause Automatic Real-Time Identification of Urban Road Traffic Congestion Based on Bayesian Network
Urban road traffic congestion is caused by various factors, such as dynamic and real-time, complexity, and changeability, and existing methods are subjective, have low accuracy and poor real-time, and are unable to automatically identify. This study proposes a multicause automatic real-time identification of urban road traffic congestion on the basis of the Bayesian network. First, the method performs systematic mechanism analysis and simulation verification on the relationship between the dynamic observable variables of urban road traffic and the multiple congestion causes to construct the Bayesian network structure. Second, the obtained measured historical data are used for parameter learning and training to obtain the complete Bayesian network model. Finally, multiple causes of traffic congestion can be automatically and simultaneously identified in real time when inputting the observable variables of traffic under road working conditions into the Bayesian network model. This method has high flexibility that can help express the correlation of nodes better and has strong interpretability, which can fully use expert experience and knowledge and achieve automatization in real time. The results in the research on Quanxiu Street, Quanzhou City show that the construction of the multicause automatic real-time identification of urban road traffic congestion based on the Bayesian network is reasonable. Five congestion causes have higher recognition accuracy rates than contrast methods, which include pedestrian influence, peak traffic, parking occupied road, unreasonable signal timing, and impact of traffic crossing the road.
Multicause Automatic Real-Time Identification of Urban Road Traffic Congestion Based on Bayesian Network
Cao, Yu (author) / Wang, Cheng (author) / Yang, Yue-ming (author) / Xu, Jiang-tao (author) / Gao, Yue-er (author)
2020-12-01
112020-01-01 pages
Article (Journal)
Electronic Resource
Unknown
Identifying Traffic Congestion Patterns of Urban Road Network Based on Traffic Performance Index
| DOAJ | 2023
Diagnosis and Prediction of Traffic Congestion on Urban Road Networks Using Bayesian Networks
| British Library Online Contents | 2016