Attribute trajectory analysis: a framework to analyse attribute changes using trajectory analysis techniques

ABSTRACT

Trajectory analysis has attracted growing attention in the research field of geography. Beyond traditional moving object trajectories, another type of trajectory exists in which the coordinates are object attributes rather than geographical coordinates. In this paper, a framework to analyse these so-called attribute trajectories is proposed that uses four techniques typically employed in the analysis of moving object trajectories: the Reeb graph, the similarity matrix, the convoy and the mega-convoy. The Reeb graph provides the ability to visualise the temporal dynamics of attribute similarities. The similarity matrix is a supplement of the Reeb graph whose purpose is to visualise the pairwise similarities among the attributes. Moreover, the similarity matrix forms a basis for clustering. The convoy highlights objects whose attributes remain similar for a sufficiently long period. The mega-convoy reduces the number of convoys and reveals their evolutionary histories by merging overlapping convoys. A small real-world meteorological dataset is used as an example to illustrate the attribute trajectory analysis framework and the techniques. This paper aims to form a starting point for applying trajectory analysis techniques in many research fields.

KEYWORDS:

• Attribute trajectory
• Reeb graph
• similarity matrix
• convoy
• mega-convoy

Acknowledgements

The authors would like to thank the China Scholarship Council (CSC) for funding the research of Long Zhang. The authors would also like to thank the anonymous reviewers for their valuable comments and suggestions to improve the manuscript.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by the China Scholarship council (CSC) [grant number 201406860007].