Measuring similarity of mobile phone user trajectories– a Spatio-temporal Edit Distance method
The rapid development of information and communication technologies (ICTs) has provided rich data sources for analyzing, modeling, and interpreting human mobility patterns. This paper contributes to this research area by developing the Spatio-temporal Edit Distance measure, an extended
algorithm to determine the similarity between user trajectories based on call detailed records (CDRs). We improve the traditional Edit Distance algorithm by incorporating both spatial and temporal information into the cost functions. The extended algorithm can preserve both space and time
information from string-formatted CDR data. The novel method is applied to a large data set from Northeast China in order to test its effectiveness. Three types of analyses are presented for scenarios with and without the effect of time: (1) Edit Distance with spatial information; (2) Edit
Distance with time as a factor in the cost function; and (3) Edit Distance with time as a constraint in partitioning trajectories. The outcomes of this research contribute to both methodological and empirical perspectives. The extended algorithm performs well for measuring low-resolution tracking
information in CDRs, as well as facilitating the interpretation of user mobility patterns in the age of instant access.
Keywords: edit distance; human mobility patterns; mobile phone data sets; time series; trajectory similarity measure
Document Type: Research Article
Affiliations: Institute of Cartography and Geoinformation, ETH Zurich, 8093, Zurich, Switzerland
Publication date: 04 March 2014
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Ingenta Connect is not responsible for the content or availability of external websites
- Access Key
- Free content
- Partial Free content
- New content
- Open access content
- Partial Open access content
- Subscribed content
- Partial Subscribed content
- Free trial content