Abstract Traffic planning is a very important tool that enables planners to determine solutions for traffic congestion. In practice, there are many difficulties, including a lack of data, that have prevented traffic planners from fully understanding urban travel characteristics, and thus the implementation of some traffic planning projects has not met the travel demands of urban residents. The traditional method is to estimate travel demand by combining the nature of land use and the intensity of development. However, for traffic planning, the prediction of factors, such as the travel distance, commuting distance, and other indicators, relies on a “four-stage model,” which needs large amounts of difficult to obtain modeling data, and the results do not have a high degree of precision. In addition it is not practical for all applications. In this study, we used cellular data to extract the distribution of people, including the distribution of their jobs, travel, and other parameters, and established a city scape based only on job distribution, with spatial location data used to model the travel characteristics. Based on the parameters of population density, job density, balance of jobs and residents, distance to the city center, and distance to the workplace, the trip density, the daily trip distance, and the distance commuted, a predictive model for different urban areas was established by multiple linear regression. The correlation coefficients of the model indicated that the accuracy of trip density prediction was very high, while the accuracy of daily trip distance and distance commuted was lower, but the model was considered suitable for practical application.
Application of Cellular Data in Traffic Planning
2017-09-28
24 pages
Article/Chapter (Book)
Electronic Resource
English
Thinking About Application of Refined Travel Data in Traffic Planning
Springer Verlag | 2022
|Traffic indication equipment for traffic planning, and traffic planning system
European Patent Office | 2021
|