期刊
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
卷 30, 期 9, 页码 1785-1805出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/13658816.2016.1139119
关键词
Activity pattern; region of interest; behaviour similarity; clustering; time geography
类别
资金
- China Scholarship Council (CSC)
- Engineering and Physical Sciences Research Council [EP/J004197/1] Funding Source: researchfish
- EPSRC [EP/J004197/1] Funding Source: UKRI
Datasets collecting the ever-changing position of moving individuals are usually big and possess high spatial and temporal resolution to reveal activity patterns of individuals in greater detail. Information about human mobility, such as 'when, where and why people travel', is contained in these datasets and is necessary for urban planning and public policy making. Nevertheless, how to segregate the users into groups with different movement and behaviours and generalise the patterns of groups are still challenging. To address this, this article develops a theoretical framework for uncovering space-time activity patterns from individual's movement trajectory data and segregating users into subgroups according to these patterns. In this framework, individuals' activities are modelled as their visits to spatio-temporal region of interests (ST-ROIs) by incorporating both the time and places the activities take place. An individual's behaviour is defined as his/her profile of time allocation on the ST-ROIs she/he visited. A hierarchical approach is adopted to segregate individuals into subgroups based upon the similarity of these individuals' profiles. The proposed framework is tested in the analysis of the behaviours of London foot patrol police officers based on their GPS trajectories provided by the Metropolitan Police.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据