Matching Detections to Events in Time Series

• Michel Reis Centro Federal de Educação Tecnológica Celso Suckow da Fonseca (CEFET/RJ)
• Rebecca Salles INRIA https://orcid.org/0000-0002-1001-3839
• Geraldo Xexéo Universidade Federal do Rio de Janeiro (UFRJ)
• Rafaelli Coutinho Centro Federal de Educação Tecnológica Celso Suckow da Fonseca (CEFET/RJ)
• Eduardo Ogasawara Centro Federal de Educação Tecnológica Celso Suckow da Fonseca (CEFET/RJ)

DOI: https://doi.org/10.5753/sbbd.2024.243275

Resumo

SoftED metrics introduce a soft evaluation of event detection methods in time series, incorporating fuzzy logic concepts to provide temporal tolerance in detections. However, these metrics face challenges associating detections with events, especially in cases with multiple associations between detections and events. In this work, we propose structuring this association problem within the graph theory paradigm, approaching it as a bipartite graph matching problem. For this, the Hungarian algorithm is employed to solve the association problem. The results demonstrate the effectiveness of the proposed approach, highlighting the impact of improvements in the associations between detections and events.

Palavras-chave: Event Detection, Soft Metrics

Referências

Bollobás, B. (1979). Graph Theory, volume 63 of Graduate Texts in Mathematics.

Springer, New York, NY. Guralnik, V. and Srivastava, J. (1999). Event Detection from Time Series Data. In Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’99, pages 33–42, New York, NY, USA. ACM.

Hanssens, D. M., Parsons, L. J., and Schultz, R. L. (2003). Market Response Models: Econometric and Time Series Analysis. Springer, Boston, Mass., 2nd edition.

Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1-2):83–97.

Lavin, A. and Ahmad, S. (2016). Evaluating real-time anomaly detection algorithms - The numenta anomaly benchmark. In Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015, pages 38 – 44.

Pimentel, M. A., Clifton, D. A., Clifton, L., and Tarassenko, L. (2014). A review of novelty detection. Signal Processing, 99:215 – 249.

Salles, R., Escobar, L., Baroni, L., Zorrilla, R., Ziviani, A., Kreischer, V., Delicato, F., Pires, P. F., Maia, L., Coutinho, R., Assis, L., and Ogasawara, E. (2020). Harbinger: Um framework para integração e análise de métodos de detecção de eventos em séries temporais. In Anais do Simpósio Brasileiro de Banco de Dados (SBBD), pages 73–84. SBC.

Salles, R., Lima, J., Coutinho, R., Pacitti, E., Masseglia, F., Akbarinia, R., Chen, C., Garibaldi, J., Porto, F., and Ogasawara, E. (2023). SoftED: Metrics for Soft Evaluation of Time Series Event Detection. SoftED, arXiv, 2023-04-04.

Tatbul, N., Lee, T. J., Zdonik, S., Alam, M., and Gottschlich, J. (2018). Precision and recall for time series. In Advances in Neural Information Processing Systems, volume 2018-December, pages 1920 – 1930.

Tettamanzi, A. and Tomassini, M. (2013). Soft Computing: Integrating Evolutionary, Neural, and Fuzzy Systems. Springer Science & Business Media.

Zadeh, L. (1965). Fuzzy sets. Information and Control, 8(3):338 – 353.