Abstract
Time Series forecasting is of high interest in the Big Data ecosystem. A larger data volume accessible in industry and science, and a higher profit from more accurate predictions have generated a growing application of Deep Learning techniques in the Time Series forecasting. In this work, the improvement of the forecasting capacity of Convolutional Neural Networks and Recurrent Neural Networks when using as input the trend, seasonal and remainder time series generated by the Seasonal and Trend decomposition using Loess, instead of the original time series observations, is evaluated. The benchmark used in this work is composed of eight seasonal time series with different lengths and origins. Besides, Convolutional Neural Networks and Recurrent Neural Networks, comparisons with Multilayer Perceptrons are also undertaken. As a consequence, an improvement in the forecasting capacity when replacing the original observations by their decomposition in Convolutional Neural Networks-based forecasting is stated.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Regarding the previous efforts in the analysis of the \(^{222}Rn\) level at Canfranc Underground Laboratory (LSC), in [20] the initial efforts for modelling this time series using classical and deep-learning-based approaches are shown. In this paper, the times series is modelled using CNN, being the main focus on the monthly forecasting capacity for scheduling maintenance operations of the experiment hosted at LSC. The LSC is composed of diverse halls for hosting scientific experiments with requirements of very low-background. The two main halls, Hall A and Hall B —which are contiguous—, have instruments for measuring the level of \(^{222}Rn\).
- 2.
In [1] an assessment of the relationship between the \(SO_2\) and the total suspended particulate levels and mortality in Madrid during the period 1986–1992 is presented. In this study the time series analysis is based on multivariate autoregressive integrated moving-average (ARIMA). Other publications relating Madrid acoustic or air pollution with population health can be found in [8, 18].
References
Alberdi Odriozola, J.C., Díaz Jiménez, J., Montero Rubio, J.C., Mirón Pérez, I.J., Pajares Ortíz, M.S., Ribera Rodrigues, P.: Air pollution and mortality in Madrid, Spain: a time-series analysis. Int. Arch. Occup. Environ. Health 71(8), 543–549 (1998). https://doi.org/10.1007/s004200050321
Births Time Series. https://datamarket.com/data/set/22nv/monthly-new-york-city-births-unknown-scale-jan-1946-dec-1959
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press Inc., New York (1995)
Chniti, G., Bakir, H., Zaher, H.: E-commerce time series forecasting using LSTM neural network and support vector regression. In: Proceedings of the International Conference on Big Data and Internet of Thing, BDIOT 2017, pp. 80–84. ACM, New York (2017). https://doi.org/10.1145/3175684.3175695
Chollet, F., et al.: Keras (2015). https://github.com/fchollet/keras
Cleveland, R.B., Cleveland, W.S., McRae, J., Terpenning, I.: STL: a seasonal-trend decomposition procedure based on loess. J. Off. Stat. 6(1), 3–33 (1990)
Díaz, J., García, R., Ribera, P., Alberdi, J.C., Hernández, E., Pajares, M.S., Otero, A.: Modeling of air pollution and its relationship with mortality and morbidity in Madrid, Spain. Int. Arch. Occup. Environ. Health 72(6), 366–376 (1999). https://doi.org/10.1007/s004200050388
Gamboa, J.C.B.: Deep learning for time-series analysis. CoRR abs/1701.01887 (2017). http://arxiv.org/abs/1701.01887
García, S., Fernández, A., Luengo, J., Herrera, F.: A study of statistical techniques and performance measures for genetics-based machine learning: accuracy and interpretability. Soft Comput. 13(10), 959–977 (2009)
García, S., Molina, D., Lozano, M., Herrera, F.: A study on the use of non-parametric tests for analyzing the evolutionary algorithms’ behaviour: a case study on the CEC’2005 special session on real parameter optimization. J. Heuristics 15(6), 617–644 (2009)
Garcia-Pedrero, A., Gomez-Gil, P.: Time series forecasting using recurrent neural networks and wavelet reconstructed signals. In: 2010 20th International Conference on Electronics Communications and Computers (CONIELECOMP), pp. 169–173, February 2010. https://doi.org/10.1109/CONIELECOMP.2010.5440775
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
Lago, J., Ridder, F.D., Schutter, B.D.: Forecasting spot electricity prices: deep learning approaches and empirical comparison of traditional algorithms. Appl. Energy 221, 386–405 (2018). https://doi.org/10.1016/j.apenergy.2018.02.069. http://www.sciencedirect.com/science/article/pii/S030626191830196X
LeCun, Y.: Generalization and network design strategies. University of Toronto, Technical report (1989)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791
Linares, C., Díaz, J., Tobías, A., Miguel, J.M.D., Otero, A.: Impact of urban air pollutants and noise levels over daily hospital admissions in children in Madrid: a time series analysis. Int. Arch. Occup. Environ. Health 79(2), 143–152 (2006). https://doi.org/10.1007/s00420-005-0032-0
Lipton, Z.C.: A critical review of recurrent neural networks for sequence learning. CoRR abs/1506.00019 (2015). http://arxiv.org/abs/1506.00019
Méndez-Jiménez, I., Cárdenas-Montes, M.: Modelling and forecasting of the \(^{222}{R}n\) radiation level time series at the Canfranc Underground Laboratory. In: de CosJuez, F. (ed.) HAIS 2018. LNCS, vol. 10870, pp. 158–170. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-92639-1_14
Passengers Time Series: https://datamarket.com/data/set/22u3/international-airline-passengers-monthly-totals-in-thousands-jan-49-dec-60
Qiu, X., Zhang, L., Ren, Y., Suganthan, P.N., Amaratunga, G.A.J.: Ensemble deep learning for regression and time series forecasting. In: 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning, CIEL 2014, Orlando, FL, USA, 9–12 December 2014, pp. 21–26 (2014). https://doi.org/10.1109/CIEL.2014.7015739
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986). https://doi.org/10.1038/323533a0
Walid, Alamsyah: Recurrent neural network for forecasting time series with long memory pattern. J. Phys.: Conf. Ser. 824(1), 012038 (2017). http://stacks.iop.org/1742-6596/824/i=1/a=012038
Wang, H.Z., Li, G.Q., Wang, G.B., Peng, J.C., Jiang, H., Liu, Y.T.: Deep learning based ensemble approach for probabilistic wind power forecasting. Appl. Energy 188, 56–70 (2017). https://doi.org/10.1016/j.apenergy.2016.11.111. http://www.sciencedirect.com/science/article/pii/S0306261916317421
Wang, Z., Yan, W., Oates, T.: Time series classification from scratch with deep neural networks: a strong baseline. CoRR abs/1611.06455 (2016). http://arxiv.org/abs/1611.06455
Zheng, Y., Liu, Q., Chen, E., Ge, Y., Zhao, J.L.: Time series classification using multi-channels deep convolutional neural networks. In: Li, F., Li, G., Hwang, S., Yao, B., Zhang, Z. (eds.) WAIM 2014. LNCS, vol. 8485, pp. 298–310. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-08010-9_33
Zheng, Y., Liu, Q., Chen, E., Ge, Y., Zhao, J.L.: Exploiting multi-channels deep convolutional neural networks for multivariate time series classification. Front. Comput. Sci. 10(1), 96–112 (2016). https://doi.org/10.1007/s11704-015-4478-2
Acknowledgment
The research leading to these results has received funding by the Spanish Ministry of Economy and Competitiveness (MINECO) for funding support through the grant FPA2016-80994-C2-1-R, and “Unidad de Excelencia María de Maeztu”: CIEMAT - FÍSICA DE PARTÍCULAS through the grant MDM-2015-0509.
IMJ is co-funded in a 91.89 percent by the European Social Fund within the Youth Employment Operating Program, for the programming period 2014–2020, as well as Youth Employment Initiative (IEJ). IMJ is also co-funded through the Grants for the Promotion of Youth Employment and Implantation of Youth Guarantee in Research and Development and Innovation (I+D+i) from the MINECO.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Méndez-Jiménez, I., Cárdenas-Montes, M. (2018). Time Series Decomposition for Improving the Forecasting Performance of Convolutional Neural Networks. In: Herrera, F., et al. Advances in Artificial Intelligence. CAEPIA 2018. Lecture Notes in Computer Science(), vol 11160. Springer, Cham. https://doi.org/10.1007/978-3-030-00374-6_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-00374-6_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00373-9
Online ISBN: 978-3-030-00374-6
eBook Packages: Computer ScienceComputer Science (R0)