Generalization of Constrained Space-Time Sequence Mining

• Antonio Castro Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)
• Heraldo Borges Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)
• Ricardo Campisano Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)
• Esther Pacitti University of Montpellier
• Fabio Porto National Laboratory for Scientific Computing (LNCC)
• Rafaelli Coutinho Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ) http://orcid.org/0000-0002-1735-1718
• Eduardo Ogasawara Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ) http://orcid.org/0000-0002-0466-0626

DOI: https://doi.org/10.5753/sbbd.2021.17891

Abstract

Spatiotemporal patterns bring knowledge of sequences of events, place and time when they occur. Finding such patterns is a complex task and one of great value for different domains. However, not all patterns are frequent across an entire dataset, often occurring in restricted space and time. This work formalizes the Mining of Restricted Sequences in Space and Time, without the use of previous restrictions of time and space, allowing different sequence sizes, time intervals and space (in three dimensions) to present such patterns. It also brings validation with a tested implementation on a real seismic dataset. Resulting in a sensitivity analysis and evaluation of the use of resources that indicate the validity and feasibility of the solution.

Keywords: Pattern Mining, Sequence Mining, Spatiotemporal

References

H. Alatrista-Salas, S. Bringay, F. Flouvat, N. Selmaoui-Folcher, and M. Teisseire (2016). Spatio-sequential patterns mining: Beyond the boundaries. Intelligent Data Analysis, 20(2):293–316.

R. Campisano, H. Borges, F. Porto, F. Perosi, E. Pacitti, F. Masseglia, and E. Ogasawara (2018). Discovering tight space-time sequences. In Lecture Notes in Computer Science, volume 11031 LNCS, pages 247–257.

C. Flamand, M. Fabregue, S. Bringay, V. Ardillon, P. Quénel, J.C. Desenclos, and M. Teisseire (2014). Mining local climate data to assess spatiotemporal dengue fever epidemic patterns in French Guiana. Journal of the American Medical Informatics Association, 21(e2):e232–240.

Y. Huang, L. Zhang, and P. Zhang (2008). A framework for mining sequential patterns from spatio-temporal event data sets. IEEE Transactions on Knowledge and Data Engineering, 20(4):433–448.

B. Koseoglu, E. Kaya, S. Balcisoy, and B. Bozkaya (2020). ST Sequence Miner: visualization and mining of spatio-temporal event sequences. Visual Computer, 36(10-12):2369–2381.

K. Li and Y. Fu (2014). Prediction of human activity by discovering temporal sequence patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8):1644–1657.

B. Saleh and F. Masseglia (2008). Time aware mining of itemsets. In Proceedings of the International Workshop on Temporal Representation and Reasoning, pages 93–97.