Abstract
In this paper, a hybrid data augmentation technique for short-term time series prediction is proposed in order to overcome the underfitting problem in deep learning models based on recurrent neural networks such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The proposal hybrid technique consists of the combination of two basic data augmentation techniques that are generally used for time series classification, these are: time-warping and jittering. Time-warping allows the generation of synthetic data between each pair of values in the time series, extending its length, while jittering allows the synthetic data generated to be non-linear. To evaluate the proposal technique, it’s experimented with three non-seasonal short-term time series of Perú: CO2 emissions per capita, renewable energy consumption and Covid-19 positive cases, it is considered that predicting non-seasonal time series is more difficult than seasonal ones. The results show that the regression models based on recurrent neural networks using the selected time series with data augmentation improve results between 16.318% and 42.1426%.
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 subscriptionsReferences
Yeomans, J., Thwaites, S., Robertson, W.S.P., Booth, D., Ng, B., Thewlis, D.: Simulating time-series data for improved deep neural network performance. IEEE Access 7, 131248–131255 (2019)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(60), 1–48 (2019)
Rashid, K.M., Louis, J.: Times-series data augmentation and deep learning for construction equipment activity recognition. Adv. Eng. Inform. 42, 1–12 (2019)
Iwana, B.K.; Uchida, S.: Time series data augmentation for neural networks by time warping with a discriminative teacher. arxiv.org (2020)
Rashid, K.M., Louis J.: Window-warping: a time series data augmentation of IMU data for construction equipment activity identification. In: 36 International Symposium on Automation and Robotics in Construction (ISARC 2019), Banff, Canada (2019)
Le Guennec, A., Malinowski, S., Tavenard, R.: Data augmentation for time series classification using convolutional neural networks. In: ECML/PKDD Workshop on AALTD (2016)
Kamycky, K., Kapuscinski, T., Oszust, M.: Data augmentation with suboptimal warping for time-series classification. Sensors 20(98), 1–15 (2020)
Wen, Q., Sun, L., Song, X., Gao, J., Wang, X., Xu, H.: Time series data augmentation for deep learning: a survey. Arxiv.org, pp. 1–7 (2020)
Salinas, D., Flunkert, V., Gasthaus, J.: DeepAR: probabilistic forecasting with autoregressive recurrent networks. Arxiv.org, pp. 1–12 (2017)
Wen, R., Torkkola, K., Narayanaswamy, B., Madeka, D.: A multi-horizon quantile recurrent forecaster. Arxiv.org, pp. 1–9 (2018)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Rodriguez, C., Tupac, Y., Pucheta, J., Juarez, G., Franco, L., Otaño, P.: Time-series prediction with BEMCA approach application to short rainfall series. In: IEEE LA-CCI, Arequipa, Peru (2017)
Panapongpakom, T., Banjerdpongchai, D.: Short-term load forecast for energy management system using time series analysis and neural network method with average true range. In: ICA-SYMP, Bangkok, Thailand (2019)
Hans, C., Klages, E.: Very short term time-series forecasting of solar irradiance without exogenous inputs. Arxiv.org, pp. 1–13 (2020)
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1798–1828 (2013)
Flores, A., Tito, H., Centty, D.: Comparison of hybrid recurrent neural networks for univariate time series forecasting. In: Arai, K., Kapoor, S., Bhatia, R. (eds.) IntelliSys 2020. AISC, vol. 1250, pp. 375–387. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-55180-3_28
Flores, A., Tito, H., Centty, D.: Recurrent neural networks for meteorological time series imputation. Int. J. Adv. Comput. Sci. Appl. (IJACSA) 11(3), 482–487 (2020)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Appendix
Appendix
APPENDIX 1. Javascript Code for Proposal Technique of Data Augmentation
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Flores, A., Tito-Chura, H., Apaza-Alanoca, H. (2021). Data Augmentation for Short-Term Time Series Prediction with Deep Learning. In: Arai, K. (eds) Intelligent Computing. Lecture Notes in Networks and Systems, vol 284. Springer, Cham. https://doi.org/10.1007/978-3-030-80126-7_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-80126-7_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80125-0
Online ISBN: 978-3-030-80126-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)