As the main body of urban traffic, commuting travel can help to determine the state of urban road traffic. With the quick development of big data technology, how to identify the urban road traffic state quickly, accurately, and at low cost is the only way to realize the intelligent transportation system. Based on the identification of commuting travel by 4G mobile phone signaling data, convolutional neural network (CNN) which can solve urban network problems was applied to the road traffic state identification problem for the first time. Taking the traveling OD and commuting OD as model input, the state mode was extracted from the historical data to achieve accurate capture of the relationship between traffic demand and traffic operation status in the designed CNN model. The results show that using mobile phone data to extract traveling OD and commuting OD as the data input of the CNN model can better identify the urban road traffic state, and the model has an accuracy of 88.4%.
Urban Road Traffic State Identification Based on Mobile Phone Signaling Data and Commuting Travel Identification
20th COTA International Conference of Transportation Professionals ; 2020 ; Xi’an, China (Conference Cancelled)
CICTP 2020 ; 39-49
2020-12-09
Conference paper
Electronic Resource
English
European Patent Office | 2020
|European Patent Office | 2022
|Travel purpose identification based on mobile phone signaling data and Bayesian network
British Library Conference Proceedings | 2022
|Urban traffic model construction method fusing mobile phone signaling and travel survey data
European Patent Office | 2023
|Traffic travel model construction method based on mobile phone signaling data
European Patent Office | 2021
|