{"title":"A spatiotemporal knowledge graph-based method for identifying individual activity locations from mobile phone data","authors":"Jian Li , Tian Gan , Weifeng Li , Yuhang Liu","doi":"10.1016/j.jtrangeo.2025.104157","DOIUrl":null,"url":null,"abstract":"<div><div>In recent years, mobile phone data has been widely used for human mobility analytics. Identifying individual activity locations is the fundamental step for mobile phone data processing. Current methods typically aggregate spatially adjacent location records over multiple days to identify activity locations. However, only considering spatial relationships while overlooking temporal ones may lead to inaccurate activity location identification, and also affect activity pattern analysis. In this study, we propose a spatiotemporal knowledge graph-based (STKG) method for identifying activity locations from mobile phone data. An STKG is designed and constructed to describe individual mobility characteristics. The spatial and temporal relationships of individual stays are inferred and transformed into a spatiotemporal graph. The modularity-optimization community detection algorithm is applied to identify stays with dense spatiotemporal relationships, which are considering as activity locations. A case study in Shanghai was conducted to verify the performance of the proposed method. The results reveal a reasonable level of agreement between the spatial distribution of nighttime activity locations identified by the STKG-based method and the residential locations derived from household travel surveys data, with an R-squared value of 0.53. Compared with two baseline methods, the STKG-based method can limit an additional 45 % of activity locations with the longest daytime stay within a reasonable spatial range; In addition, the STKG-based method exhibit lower standard deviation in the start and end times of activities across different days, performing approximately 10–20 % better than the two baseline methods. Moreover, the STKG-based method effectively distinguishes between locations that are geographically close but exhibit different temporal patterns. These findings demonstrate the effectiveness of STKG-based method in enhancing both spatial precision and temporal interpretability.</div></div>","PeriodicalId":48413,"journal":{"name":"Journal of Transport Geography","volume":"124 ","pages":"Article 104157"},"PeriodicalIF":5.7000,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Transport Geography","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0966692325000481","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECONOMICS","Score":null,"Total":0}
引用次数: 0
Abstract
In recent years, mobile phone data has been widely used for human mobility analytics. Identifying individual activity locations is the fundamental step for mobile phone data processing. Current methods typically aggregate spatially adjacent location records over multiple days to identify activity locations. However, only considering spatial relationships while overlooking temporal ones may lead to inaccurate activity location identification, and also affect activity pattern analysis. In this study, we propose a spatiotemporal knowledge graph-based (STKG) method for identifying activity locations from mobile phone data. An STKG is designed and constructed to describe individual mobility characteristics. The spatial and temporal relationships of individual stays are inferred and transformed into a spatiotemporal graph. The modularity-optimization community detection algorithm is applied to identify stays with dense spatiotemporal relationships, which are considering as activity locations. A case study in Shanghai was conducted to verify the performance of the proposed method. The results reveal a reasonable level of agreement between the spatial distribution of nighttime activity locations identified by the STKG-based method and the residential locations derived from household travel surveys data, with an R-squared value of 0.53. Compared with two baseline methods, the STKG-based method can limit an additional 45 % of activity locations with the longest daytime stay within a reasonable spatial range; In addition, the STKG-based method exhibit lower standard deviation in the start and end times of activities across different days, performing approximately 10–20 % better than the two baseline methods. Moreover, the STKG-based method effectively distinguishes between locations that are geographically close but exhibit different temporal patterns. These findings demonstrate the effectiveness of STKG-based method in enhancing both spatial precision and temporal interpretability.
期刊介绍:
A major resurgence has occurred in transport geography in the wake of political and policy changes, huge transport infrastructure projects and responses to urban traffic congestion. The Journal of Transport Geography provides a central focus for developments in this rapidly expanding sub-discipline.