From small sets of GPS trajectories to detailed movement profiles: quantifying personalized trip-dependent movement diversity

ABSTRACT

The ubiquity of personal sensing devices has enabled the collection of large, diverse, and fine-grained spatio-temporal datasets. These datasets facilitate numerous applications from traffic monitoring and management to location-based services. Recently, there has been an increasing interest in profiling individuals' movements for personalized services based on fine-grained trajectory data. Most approaches identify the most representative paths of a user by analyzing coarse location information, e.g., frequently visited places. However, even for trips that share the same origin and destination, individuals exhibit a variety of behaviors (e.g., a school drop detour, a brief stop at a supermarket). The ability to characterize and compare the variability of individuals' fine-grained movement behavior can greatly support location-based services and smart spatial sampling strategies. We propose a TRip DIversity Measure --TRIM – that quantifies the regularity of users' path choice between an origin and destination. TRIM effectively captures the extent of the diversity of the paths that are taken between a given origin and destination pair, and identifies users with distinct movement patterns, while facilitating the comparison of the movement behavior variations between users. Our experiments using synthetic and real datasets and across geographies show the effectiveness of our method.

KEYWORDS:

• Personalized movement profile
• Trip Diversity
• prefix tree
• GPS trajectory

Acknowledgments

This research is supported by a Discovery Project grant of the Australian Research Council (DP170100153).

Data and codes availability statement

The codes that support the findings of this study are available in https://github.com/SelfHealingMapsProject/TRIM. The Geolife data, ie $D_1$ is also available following the above link. However, Sygic data, ie $D_2$, cannot be publicly shared for privacy protection reasons.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by the Australian Research Council [DP17010015].

Notes on contributors

Elham Naghizade

Dr Elham Naghizade has obtained her PhD in The School of Computing and Information Systems in 2016 followed by a postdoctoral research fellowship in the Department of Infrastructure Engineering (Geomatics discipline), The University of Melbourne. She has publications in privacy-preserving trajectory publication, spatiotemporal data mining and recommendation.

Jeffrey Chan

Dr Jeffrey Chan is a senior lecturer at RMIT University.  He completed his BEng/BSci (Hons) and PhD at the University of Melbourne, Australia and was a senior postdoctoral research at the Digital Enterprise Research Institute in Galway, Ireland.  He has published more than 90 publications in machine learning, social network analysis, recommendation and data driven optimisation, in venues such as TPAMI, TKDE, DMKD, KDD, ICDM, AAAI and IJCAI.  He has served on various conference organising committees, such as IJCAI and ASONAM.  He has also won best paper award in the ACM International Conference on Web Science  in 2011.

Martin Tomko

Dr Martin Tomko is a Senior Lecturer in spatial information science at the University of Melbourne. His research focuses on spatial interaction assisted through computational systems.He has a PhD in Geomatics from The University of Melbourne and has previously held academic positions at the University of Zurich.