Abstract
Nowadays, huge amount of data are being produced by a large and diverse family of sensors (e.g., remote sensors, biochemical sensors, wearable devices). These sensors typically measure multiple variables over time, resulting in data streams that can be profitably organized as multivariate time-series. In practical scenarios, the speed at which such information is collected often makes the data labeling a difficult task. This results in a low-data regime scenario where only a small set of labeled samples is available and standard supervised learning algorithms cannot be employed. To cope with the task of multi-variate time series classification in low-data regime scenarios, here, we propose a framework that combines convolutional neural networks (CNNs) with self-training (pseudo labeling) in a transductive setting (test data are already available at training time). Our framework, named \(ResNet^{IPL}\), wraps a CNN based classifier into an iterative procedure that, at each step, enlarges the training set with new samples and their associated pseudo labels. An experimental evaluation on several benchmarks, coming from different domains, has demonstrated the value of the proposed approach and, more generally, the ability of the deep learning approaches to effectively deal with scenarios characterized by low-data regimes.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
- 3.
Code will be available upon acceptance.
References
Buitinck, L., et al.: API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD Workshop: Languages for Data Mining and Machine Learning, pp. 108–122 (2013)
Castellanos, M.G., Bergmeir, C., Triguero, I., Rodríguez, Y., Benítez, J.M.: Self-labeling techniques for semi-supervised time series classification: an empirical study. Knowl. Inf. Syst. 55(2), 493–528 (2018)
Chen, Y., Hu, B., Keogh, E.J., Batista, G.E.A.P.A.: DTW-D: time series semi-supervised learning from a single example. In: KDD, pp. 383–391. ACM (2013)
Fawaz, H.I., Forestier, G., Weber, J., Idoumghar, L., Muller, P.: Deep learning for time series classification: a review. Data Min. Knowl. Discov. 33(4), 917–963 (2019)
Frank, J., Mannor, S., Pineau, J., Precup, D.: Time series analysis using geometric template matching. IEEE Trans. Pattern Anal. Mach. Intell. 35(3), 740–754 (2013)
Gbodjo, Y.J.E., Ienco, D., Leroux, L.: Toward spatio-spectral analysis of sentinel-2 time series data for land cover mapping. IEEE Geosci. Remote Sens. Lett. 17(2), 307–311 (2020)
Geler, Z., Kurbalija, V., Radovanovic, M., Ivanovic, M.: Comparison of different weighting schemes for the KNN classifier on time-series data. Knowl. Inf. Syst. 48(2), 331–378 (2016)
van der Maaten, L., Hinton, G.: Visualizing Data Using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Marussy, K., Buza, K.: SUCCESS: a new approach for semi-supervised classification of time-series. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013. LNCS (LNAI), vol. 7894, pp. 437–447. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38658-9_39
Saporta, A., Vu, T., Cord, M., Pérez, P.: ESL: entropy-guided self-supervised learning for domain adaptation in semantic segmentation. CoRR abs/2006.08658 (2020)
de Sousa, C.A.R., Rezende, S.O., Batista, G.E.A.P.A.: Influence of graph construction on semi-supervised learning. In: ECML/PKDD, vol. 8190, pp. 160–175 (2013)
Tan, P.N., Steinbach, M., Kumar, V.: Introduction to Data Mining, 1st edn. Addison-Wesley Longman Publishing Co. Inc., Boston (2005)
Tavenard, R., et al.: Tslearn, a machine learning toolkit for time series data. J. Mach. Learn. Res. 21(118), 1–6 (2020)
Triguero, I., García, S., Herrera, F.: Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study. Knowl. Inf. Syst. 42(2), 245–284 (2015)
Wang, X., Mueen, A., Ding, H., Trajcevski, G., Scheuermann, P., Keogh, E.J.: Experimental comparison of representation methods and distance measures for time series data. Data Min. Knowl. Discov. 26(2), 275–309 (2013)
Wang, Z., Yan, W., Oates, T.: Time series classification from scratch with deep neural networks: a strong baseline. In: IJCNN, pp. 1578–1585. IEEE (2017)
Yamaguchi, Y., Faloutsos, C., Kitagawa, H.: CAMLP: confidence-aware modulated label propagation. In: SDM, pp. 513–521. SIAM (2016)
Zhang, X., Gao, Y., Lin, J., Lu, C.: TapNet: multivariate time series classification with attentional prototypical network. In: AAAI, pp. 6845–6852 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Ienco, D., Pereira-Santos, D., de Carvalho, A.C.P.L.F. (2021). Evaluate Pseudo Labeling and CNN for Multi-variate Time Series Classification in Low-Data Regimes. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12895. Springer, Cham. https://doi.org/10.1007/978-3-030-86383-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-86383-8_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86382-1
Online ISBN: 978-3-030-86383-8
eBook Packages: Computer ScienceComputer Science (R0)