HiPerMovelets: high-performance movelet extraction for trajectory classification

ABSTRACT

In the last decade, trajectory classification has received significant attention. The vast amount of data generated on social media, the use of sensor networks, IOT devices and other Internet-enabled sources allowed the semantic enrichment of mobility data, making the classification task more challenging. Existing trajectory classification methods have mainly considered space, time and numerical data, ignoring the semantic dimensions. Only recently proposed methods as Movelets and MASTERMovelets can handle all types of dimensions. MASTERMovelets is the only method that automatically discovers the best dimension combination and subtrajectory size for trajectory classification. However, although it outperformed the state-of-the-art in terms of accuracy, MASTERMovelets is computationally expensive and results in a high dimensionality problem, which makes it unfeasible for most real trajectory datasets that contain a big volume of data. To overcome this problem and enable the application of the movelets approach on large datasets, in this paper we propose a new high-performance method for extracting movelets and classifying trajectories, called HiPerMovelets (High-performance Movelets). Experimental results show that HiPerMovelets is 10 times faster than MASTERMovelets, reduces the high-dimensionality problem, is more scalable, and presents a high classification accuracy in all evaluated datasets with both raw and semantic trajectories.

KEYWORDS:

• Data mining
• multiple aspect trajectories
• trajectory classification
• relevant subtrajectories
• movelets

Acknowledgements

This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Finance Code 001 and through the research project Big Data Analytics: Lançando Luz dos Genes ao Cosmos (CAPES/PRINT process number 88887.310782/2018-00). This work was also supported by Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq), Fundação de Amparo a Pesquisa e Inovação do Estado de Santa Catarina (FAPESC) - Project Match - co-financing of H2020 Projects - Grant 2018TR 1266.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data and codes availability statement

The data and codes that support the findings of this study are available with the identifiers at the public link: https://doi.org/10.5281/zenodo.5772281

Notes

1. http://www.fs.fed.us/pnw/starkey/data/tables/.

2. https://archive.ics.uci.edu/ml/datasets/GPS+Trajectories.

3. http://www.chorochronos.org/.

4. https://keras.io/.

Additional information

Funding

CAPES - finance code 001; CAPES/PRINT process number 88887.310782/2018-00; CNPq and Fapesc - Project Match - co-financing of H2020 - Grant 2018TR 1266.

Notes on contributors

Tarlis Tortelli Portela

Tarlis Tortelli Portela is a Ph.D. candidate at the Department of Informática e Estatística at Universidade Federal de Santa Catarina (UFSC), Florianópolis-Brazil. His research is focused on advanced geographical information science for machine learning algorithms and trajectory classification.

Jonata Tyska Carvalho

Jônata Tyska Carvalho is professor at the Department of Informática e Estatística at Universidade Federal de Santa Catarina (UFSC), Florianópolis-Brazil. His research focuses on adaptive behavior, evolutionary computation, applied machine learning, and the development of methods for analyzing complex data. He is especially interested in applications involving mobility data, health, robotics and logic circuit synthesis.

Vania Bogorny

Vania Bogorny is professor at the Department of Informática e Estatística at Universidade Federal de Santa Catarina (UFSC), Florianópolis-Brazil. Her research focuses on Big Data, mobility and sequence data science, and machine learning.