Time Series Classification using Shape Features based on Angle Statistics

• Bionda Rozin UNESP
• Daniel Carlos Guimarães Pedronette UNESP

DOI: https://doi.org/10.5753/eniac.2021.18276

Resumo

Séries temporais possuem grande aplicabilidade nos mais diversos cenários, incluindo os domínios científicos, agrícola, econômico, entre outros. Portanto, criar representações efetivas de uma série temporal é uma tarefa desafiadora, pois possibilita análises mais precisas e, consequentemente, obtenção de resultados e conclusões mais assertivas em diversas tarefas de aprendizado de máquina. Uma das principais tarefas associadas é a classificação, que pode ser realizada a partir de diferentes representações computacionais das séries temporais. Este trabalho tem como principal objetivo melhorar a eficácia de tarefas de classificação, utilizando uma representação das séries temporais obtida pelo algoritmo Beam Angle Statistics, um extrator de características de contorno baseado em estatísticas angulares.

Referências

Arica, N. and Yarman-Vural, F. (2003). Bas: a perceptual shape descriptor based on the beam angle statistics. Pattern Recognition Letters, 24:1627–1639.

Bagnall, A., Lines, J., Bostrom, A., Large, J., and Keogh, E. (2017). The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Mining and Knowledge Discovery, 31:606–660.

Bramer, M. (2007). Principles of Data Mining. Springer, London.

Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.

C. Baskaran, N. S. (2018). Time series analysis of swine u literature during 1991-2013. International Journal of Library Science and Information Management, 2:38–48.

Campbell, J. Y. and Mankiw, N. G. (1989). Consumption, Income and Interest Rates: Reinterpreting the Time Series Evidence. In NBER Macroeconomics Annual 1989, V. 4, pages 185–246. National Bureau of Economic Research, Inc.

Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3):273–297.

Deng, H., Runger, G., Tuv, E., and Vladimir, M. (2013). A time series forest for classification and feature extraction. Information Sciences, 239:142–153.

Eckmann, J.-P., Kamphorst, S., and Ruelle, D. (1987). Recurrence plots of dynamical systems. Europhysics Letters (epl), 4:973–977.

Faouzi, J. and Janati, H. (2020). pyts: A python package for time series classification. Journal of Machine Learning Research, 21(46):1–6.

Geler, Z., Kurbalija, V., Ivanovic, M., and Radovanovic, M. (2020). Weighted knn and constrained elastic distances for time-series classification. Expert Systems with Applications, 162:113829.

Mazoyer, M. and Roudart, L. (2006). A History of World Agriculture: From the Neolithic Age to the Current Crisis. Earthscan, London.

Pecora, Carroll, and Heagy (1995). Statistics for mathematical properties of maps between time series embeddings. Physical review. E, Statistical physics, plasmas, uids, and related interdisciplinary topics, 52 4:3420–3439.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2011). Scikit-learn: Machine learning in python. Journal of Machine Learning Research, 12(Oct):2825–2830.

Pincus, S. and Kalman, R. (2004). Irregularity, volatility, risk, and financial market time series. Proc. of the National Academy of Sciences of the USA, 101:13709–13714.

Pino, F. A. (2014). Sazonalidade na agricultura. Revista De Economia Agrícola (Impresso), v. 61:p. 63–93.

Saito, T. and Rehmsmeier, M. (2015). The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets. PloS one, 10:e0118432.

Schäfer, P. (2016). Scalable time series classification. Data Mining and Knowledge Discovery, 30:1273–1298.

Senin, P. and Malinchik, S. (2013). Sax-vsm: Interpretable time series classification using sax and vector space model. In 2013 IEEE 13th International Conference on Data Mining, pages 1175–1180.

Tabar, Y. R. and Halici, U. (2017). A novel deep learning approach for classification of eeg motor imagery signals. Journal of Neural Engineering, 14 1:016003.

Torres, R. d. S., Hasegawa, M., Tabbone, S., Almeida, J., dos Santos, J. A., Alberton, B., and Morellato, L. P. C. (2013). Shape-based time series analysis for remote phenology studies. In IEEE Int. Geoscience and Remote Sensing Symposium, pages 3598–3601.

Volna, E., Kotyrba, M., and Habiballa, H. (2015). Ecg prediction based on classification via neural networks and linguistic fuzzy logic forecaster. The Scientific World Journal, 2015:205749.

Wang, Z. and Oates, T. (2015a). Encoding time series as images for visual inspection and classification using tiled convolutional neural networks. In Workshops at the twentyninth AAAI conference on artificial intelligence.

Wang, Z. and Oates, T. (2015b). Imaging time-series to improve classification and imputation. In Proceedings of the 24th International Conference on Artificial Intelligence, page 3939–3945. AAAI Press.

Ye, L. and Keogh, E. (2011). Time series shapelets: A novel technique that allows accurate, interpretable and fast classification. Data Mining Know. Discovery, 22:149–182.

Zhang, Y., Gan, F., and Chen, X. (2020a). Motif difference field: An effective imagebased time series classification and applications in machine malfunction detection. In Conf. on Energy Internet and Energy System Integration (EI2), pages 3079–3083.

Zhang, Y., Hou, Y., Zhou, S., and Ouyang, K. (2020b). Encoding time series as multiscale signed recurrence plots for classification using fully convolutional networks. Sensors, 20:3818.