Back to Search Start Over

Research on the Method of Urban Jobs-Housing Space Recognition Combining Trajectory and POI Data

Authors :
Ya Zhang
Jiping Liu
Yong Wang
Yungang Cao
Youda Bai
Source :
ISPRS International Journal of Geo-Information, Vol 10, Iss 2, p 71 (2021)
Publication Year :
2021
Publisher :
MDPI AG, 2021.

Abstract

With the gradual emergence of the separation and dislocation of urban jobs-housing space, rational planning of urban jobs-housing space has become the core issue of national land-spatial planning. To study the existing relationship between workspaces and living spaces, a new method to identify jobs-housing space is proposed, which not only considers the static spatial distribution of urban public facilities but also identifies the jobs-housing space by analyzing the real mobility characteristics of people from a humanistic perspective. This method provides a new framework for the identification of urban jobs-housing space by integrating point-of-interest (POI) and trajectory data. The method involves three steps: Firstly, based on the trajectory data, we analyze the characteristics of the dynamic flow of passengers in the grid and construct the living factors and working factors to identify the distribution of jobs-housing space. Secondly, we reclassify the POIs to calculate the category ratios of different types of POIs in the grid to identify the jobs-housing space. Finally, an OR operation is performed on the results obtained by the two methods to obtain the final recognition result. We selected Haikou City as the experimental area to verify the method proposed in this paper. The experimental results show that the recognition accuracy of the travel flow model is 72.43%, the POI quantitative recognition method’s accuracy is 74.94%, and the accuracy of the method proposed in this paper is 85.90%, which is significantly higher than the accuracy of the previous two methods. Therefore, the method proposed here can serve as a reference for subsequent research on urban jobs-housing space.

Details

Language :
English
ISSN :
10020071 and 22209964
Volume :
10
Issue :
2
Database :
Directory of Open Access Journals
Journal :
ISPRS International Journal of Geo-Information
Publication Type :
Academic Journal
Accession number :
edsdoj.4da0a9e909f04463980d6632a5589eab
Document Type :
article
Full Text :
https://doi.org/10.3390/ijgi10020071