Abstract
Traditional time series forecasting models often use all available variables, including potentially irrelevant or noisy features, which can lead to overfitting and poor performance. Feature selection can help address this issue by selecting the most informative variables in the temporal and feature dimensions. However, selecting the right features can be challenging for time series models. Embedded feature selection has been a popular approach, but many techniques do not include it in their design, including deep learning methods, which can lead to less efficient and effective feature selection. This paper presents a deep learning-based method for time series forecasting that incorporates feature selection to improve model efficacy and interpretability. The proposed method uses a multidimensional layer to remove irrelevant features along the temporal dimension. The resulting model is compared to several feature selection methods and experimental results demonstrate that the proposed approach can improve forecasting accuracy while reducing model complexity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Python implementation and experimentation have been included in the following repository https://github.com/manjimnav/TSSLayer.
References
Borisov, V., Haug, J., Kasneci, G.: CancelOut: a layer for feature selection in deep neural networks. In: Proceedings of 28th International Conference on Artificial Neural Networks. Artificial Neural Networks and Machine Learning - ICANN 2019: Deep Learning, pp. 72–83 (2019)
Cancela, B., Bolón-Canedo, V., Alonso-Betanzos, A.: E2E-FS: an end-to-end feature selection method for neural networks. IEEE Trans. Pattern Anal. Mach. Intell. pp. 1–12 (2020)
CDT: California department of transportation (2015). https://pems.dot.ca.gov/
Godahewa, R., Bergmeir, C., Webb, G., Hyndman, R., Montero-Manso, P.: Electricity hourly dataset (2020)
Gómez-Losada, A., Asencio-Cortés, G., Martínez-Álvarez, F., Riquelme, J.C.: A novel approach to forecast urban surface-level ozone considering heterogeneous locations and limited information. Environ. Model. Softw. 110, 52–61 (2018)
Jiménez-Navarro, M.J., Martínez-Ballesteros, M., Sousa, I.S., Martínez-Álvarez, F., Asencio-Cortés, G.: Feature-aware drop layer (FADL): a nonparametric neural network layer for feature selection. In: Proceedings of 17th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2022), pp. 557–566 (2023)
Jiménez-Navarro, M.J., Martínez-Ballesteros, M., Martínez-Álvarez, F., Asencio-Cortés, G.: PHILNet: a novel efficient approach for time series forecasting using deep learning. Inf. Sci. 632, 815–832 (2023)
Lai, G., Chang, W., Yang, Y., Liu, H.: Modeling long- and short-term temporal patterns with deep neural networks. ACM, pp. 95–104 (2018)
Shannon, C.E.: A mathematical theory of communication. ACM SIGMOBILE Mob. Comput. Commun. Rev. 5(1), 3–55 (2001)
Yuan, D., Jiang, J., Gong, Z., Nie, C., Sun, Y.: Moldy peanuts identification based on hyperspectral images and point-centered convolutional neural network combined with embedded feature selection. Comput. Electron. Agric. 197, 106963 (2022)
Zhang, H., Wang, J., Sun, Z., Zurada, J.M., Pal, N.R.: Feature selection for neural networks using group lasso regularization. IEEE Trans. Knowl. Data Eng. 32(4), 659–673 (2020)
Zhou, H., et al.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 11106–11115 (2021)
Acknowledgements
The authors would like to thank the Spanish Ministry of Science and Innovation for the support under the projects PID2020-117954RB and TED2021-131311B, and the European Regional Development Fund and Junta de Andalucía for projects PY20-00870, PYC20 RE 078 USE and UPO-138516.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jiménez-Navarro, M.J., Martínez-Ballesteros, M., Martínez-Álvarez, F., Asencio-Cortés, G. (2023). Embedded Temporal Feature Selection for Time Series Forecasting Using Deep Learning. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2023. Lecture Notes in Computer Science, vol 14135. Springer, Cham. https://doi.org/10.1007/978-3-031-43078-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-43078-7_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43077-0
Online ISBN: 978-3-031-43078-7
eBook Packages: Computer ScienceComputer Science (R0)