Análise de Desempenho e Comparação de Técnicas de Explicabilidade em Modelos de Séries Temporais
Resumo
Séries temporais são amplamente utilizadas por representarem a evolução de fenômenos ao longo do tempo e revelarem tendências relevantes para decisões sensíveis. Por isso, quando modelos de aprendizado de máquina são aplicados à sua classificação, torna-se necessário compreender seu comportamento. Nesse contexto, a explicabilidade é essencial para validar as decisões dos modelos e garantir transparência. Assim, este trabalho analisa e compara diferentes técnicas de explicabilidade aplicadas à classificação de séries temporais, avaliando tempo de execução e custo computacional para evidenciar as vantagens e limitações das principais abordagens.Referências
Azodi, C. B., Tang, J., and Shiu, S.-H. (2020). Opening the black box: interpretable machine learning for geneticists. Trends in genetics, 36(6):442–455.
Carden, E. P. and Brownjohn, J. M. (2008). Arma modelled time-series classification for structural health monitoring of civil infrastructure. Mechanical systems and signal processing, 22(2):295–314.
chung Fu, T., lai Chung, F., Luk, R., and man Ng, C. (2008). Representing financial time series based on data point importance. Engineering Applications of Artificial Intelligence, 21(2):277–300.
Cui, Z., Chen, W., and Chen, Y. (2016). Multi-scale convolutional neural networks for time series classification. arXiv preprint arXiv:1603.06995.
Dongen, H. P. V., Ruf, T., Olofsen, E., VanHartevelt, J. H., and Kruyt, E. W. (2001). Letter to the editor: Analysis of problematic time series with the lombscargle method, a reply to ‘emphasizing difficulties in the detection of rhythms with lombscargle periodograms’. Biological Rhythm Research, 32(3):347–354.
Duell, J., Fan, X., Burnett, B., Aarts, G., and Zhou, S.-M. (2021). A comparison of explanations given by explainable artificial intelligence methods on analysing electronic health records. In 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), pages 1–4. IEEE.
El Naqa, I. and Murphy, M. J. (2015). What is machine learning? In Machine learning in radiation oncology: theory and applications, pages 3–11. Springer.
Gottman, J. M. (1981). Time-series analysis. A comprehensive introduction for social scientists.
Ji, C., Du, M., Hu, Y., Liu, S., Pan, L., and Zheng, X. (2022). Time series classification based on temporal features. Applied Soft Computing, 128:109494.
Jiang, T., Gradus, J. L., and Rosellini, A. J. (2020). Supervised machine learning: a brief primer. Behavior therapy, 51(5):675–687.
Liu, C.-L., Hsaio, W.-H., and Tu, Y.-C. (2018). Time series classification with multi-variate convolutional neural network. IEEE Transactions on industrial electronics, 66(6):4788–4797.
Liu, Q., Liu, B., and Du, Y. (2023). An algorithm to improve the performance of convolutional neural networks for tsc tasks. Engineering Reports, 5(4):e12589.
Sahatova, K. and Balabaeva, K. (2022). An overview and comparison of xai methods for object detection in computer tomography. Procedia Computer Science, 212:209–219.
Shinde, P. P. and Shah, S. (2018). A review of machine learning and deep learning applications. In 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), pages 1–6.
Šimić, I., Sabol, V., and Veas, E. (2021). Xai methods for neural time series classification: A brief review. arXiv preprint arXiv:2108.08009.
Tan, C. W., Webb, G. I., and Petitjean, F. (2017). Indexing and classifying gigabytes of time series under time warping. In Proceedings of the 2017 SIAM international conference on data mining, pages 282–290. SIAM.
Theissler, A., Spinnato, F., Schlegel, U., and Guidotti, R. (2022). Explainable ai for time series classification: a review, taxonomy and research directions. Ieee Access, 10:100700–100724.
Uribarri, G., Barone, F., Ansuini, A., and Fransén, E. (2024). Detach-rocket: sequential feature selection for time series classification with random convolutional kernels. Data Mining and Knowledge Discovery, 38(6):3922–3947.
Veerappa, M., Anneken, M., Burkart, N., and Huber, M. F. (2022). Validation of xai explanations for multivariate time series classification in the maritime domain. Journal of Computational Science, 58:101539.
Wang, W. K., Chen, I., Hershkovich, L., Yang, J., Shetty, A., Singh, G., Jiang, Y., Kotla, A., Shang, J. Z., Yerrabelli, R., et al. (2022). A systematic review of time series classification techniques used in biomedical applications. Sensors, 22(20):8016.
Ye, Q., Xia, J., and Yang, G. (2021). Explainable ai for covid-19 ct classifiers: an initial comparison study. In 2021 IEEE 34th international symposium on computer-based medical systems (CBMS), pages 521–526. IEEE.
Carden, E. P. and Brownjohn, J. M. (2008). Arma modelled time-series classification for structural health monitoring of civil infrastructure. Mechanical systems and signal processing, 22(2):295–314.
chung Fu, T., lai Chung, F., Luk, R., and man Ng, C. (2008). Representing financial time series based on data point importance. Engineering Applications of Artificial Intelligence, 21(2):277–300.
Cui, Z., Chen, W., and Chen, Y. (2016). Multi-scale convolutional neural networks for time series classification. arXiv preprint arXiv:1603.06995.
Dongen, H. P. V., Ruf, T., Olofsen, E., VanHartevelt, J. H., and Kruyt, E. W. (2001). Letter to the editor: Analysis of problematic time series with the lombscargle method, a reply to ‘emphasizing difficulties in the detection of rhythms with lombscargle periodograms’. Biological Rhythm Research, 32(3):347–354.
Duell, J., Fan, X., Burnett, B., Aarts, G., and Zhou, S.-M. (2021). A comparison of explanations given by explainable artificial intelligence methods on analysing electronic health records. In 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), pages 1–4. IEEE.
El Naqa, I. and Murphy, M. J. (2015). What is machine learning? In Machine learning in radiation oncology: theory and applications, pages 3–11. Springer.
Gottman, J. M. (1981). Time-series analysis. A comprehensive introduction for social scientists.
Ji, C., Du, M., Hu, Y., Liu, S., Pan, L., and Zheng, X. (2022). Time series classification based on temporal features. Applied Soft Computing, 128:109494.
Jiang, T., Gradus, J. L., and Rosellini, A. J. (2020). Supervised machine learning: a brief primer. Behavior therapy, 51(5):675–687.
Liu, C.-L., Hsaio, W.-H., and Tu, Y.-C. (2018). Time series classification with multi-variate convolutional neural network. IEEE Transactions on industrial electronics, 66(6):4788–4797.
Liu, Q., Liu, B., and Du, Y. (2023). An algorithm to improve the performance of convolutional neural networks for tsc tasks. Engineering Reports, 5(4):e12589.
Sahatova, K. and Balabaeva, K. (2022). An overview and comparison of xai methods for object detection in computer tomography. Procedia Computer Science, 212:209–219.
Shinde, P. P. and Shah, S. (2018). A review of machine learning and deep learning applications. In 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), pages 1–6.
Šimić, I., Sabol, V., and Veas, E. (2021). Xai methods for neural time series classification: A brief review. arXiv preprint arXiv:2108.08009.
Tan, C. W., Webb, G. I., and Petitjean, F. (2017). Indexing and classifying gigabytes of time series under time warping. In Proceedings of the 2017 SIAM international conference on data mining, pages 282–290. SIAM.
Theissler, A., Spinnato, F., Schlegel, U., and Guidotti, R. (2022). Explainable ai for time series classification: a review, taxonomy and research directions. Ieee Access, 10:100700–100724.
Uribarri, G., Barone, F., Ansuini, A., and Fransén, E. (2024). Detach-rocket: sequential feature selection for time series classification with random convolutional kernels. Data Mining and Knowledge Discovery, 38(6):3922–3947.
Veerappa, M., Anneken, M., Burkart, N., and Huber, M. F. (2022). Validation of xai explanations for multivariate time series classification in the maritime domain. Journal of Computational Science, 58:101539.
Wang, W. K., Chen, I., Hershkovich, L., Yang, J., Shetty, A., Singh, G., Jiang, Y., Kotla, A., Shang, J. Z., Yerrabelli, R., et al. (2022). A systematic review of time series classification techniques used in biomedical applications. Sensors, 22(20):8016.
Ye, Q., Xia, J., and Yang, G. (2021). Explainable ai for covid-19 ct classifiers: an initial comparison study. In 2021 IEEE 34th international symposium on computer-based medical systems (CBMS), pages 521–526. IEEE.
Publicado
19/07/2026
Como Citar
SILVA, Matheus Leandro de Melo; CRUZ, Lívia Almada; MAGALHÃES, Regis Pires; COUTINHO, Emanuel Ferreira.
Análise de Desempenho e Comparação de Técnicas de Explicabilidade em Modelos de Séries Temporais. In: WORKSHOP EM DESEMPENHO DE SISTEMAS COMPUTACIONAIS E DE COMUNICAÇÃO (WPERFORMANCE), 25. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 58-69.
ISSN 2595-6167.
DOI: https://doi.org/10.5753/wperformance.2026.19620.
