Abstract
Time series forecasting predicts values in future timestamps based on historically observed series information. Algorithms based on deep neural networks such as Temporal Convolution Network(TCN) have outperformed traditional methods such as Autoregressive Integrated Moving Average Model(ARIMA). However, most existing deep learning approaches suffer from the insufficient ability to capture the seasonality features in series adequately since the network structure ignores the fact that the importance of points the series varies a lot. The local context that reflects a sub-segment of seasonality can indicate potential patterns of the series based on the periodicity. Therefore, we tend to exploit local information from historical records. To this end, we develop a novel strategy to extract local context sensitivity information and integrate them into the current state-of-the-art TCN model, namely LS-TCN. This information enables an improvement in capturing the series pattern and fluctuation, as well as providing transferable guidance for forecasting in the next steps. Experiments conducted on three different real-world series datasets demonstrate that our method significantly outperforms the state-of-the-art models, especially in autocorrelation series corpus.
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
References
Cho, C.H., Lee, G.Y., Tsai, Y.L., Lan, K.C.: Toward stock price prediction using deep learning. In: Proceedings of UCC, pp. 133–135 (2019)
Cirstea, R.G., Micu, D.V., Muresan, G.M., Guo, C., Yang, B.: Correlated time series forecasting using multi-task deep neural networks. In: Proceedings of CIKM, pp. 1527–1530 (2018)
Dau, H.A., Begum, N., Keogh, E.: Semi-supervision dramatically improves time series clustering under dynamic time warping. In: Proceedings of CIKM, pp. 999–1008 (2016)
Farha, Y.A., Gall, J.: Ms-tcn: multi-stage temporal convolutional network for action segmentation. In: Proceedings of ICPR, pp. 3575–3584 (2019)
Fu, R., Zhang, Z., Li, L.: Using lstm and gru neural network methods for traffic flow prediction. In: Proceedings of YAC, pp. 324–328 (2016)
Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: proceedings of ICPR, pp. 156–165 (2017)
Li, C.E., Chang, Y.I.: A time-position join method for periodicity mining in time series databases. In: Proceedings of ICS, pp. 294–299 (2016)
Li, D., Bissyande, T.F.D.A., Klein, J., Le Traon, Y.: Time series classification with discrete wavelet transformed data: insights from an empirical study. In: Proceedings of SEKE (2016)
Li, S., et al.: Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. In: Proceedings of NIPS, pp. 5243–5253 (2019)
Li, Z., Zhang, H., Wu, S., Zhao, Y.: Similarity measure of time series based on feature extraction. In: Proceedings of ICCCBDA, pp. 13–16 (2020)
Liu, Y., Dong, H., Wang, X., Han, S.: Time series prediction based on temporal convolutional network. In: Proceedings of ICIS, pp. 300–305 (2019)
Malhotra, P., Vig, L., Shroff, G., Agarwal, P.: Long short term memory networks for anomaly detection in time series. Proc. ESANN 89, 89–94 (2015)
van den Oord, A., et al: A generative model for raw audio. In: Proceedings of ISCASSW, pp. 125–125 (2016)
Rodrigues, M.W., Zárate, L.E.: Time series analysis using synthetic data for monitoring the temporal behavior of sensor signals. In: Proceedings of SMC, pp. 453–458 (2019)
Siami-Namini, S., Tavakoli, N., Siami Namin, A.: A comparison of arima and lstm in forecasting time series. In: Proceedings of ICMLA, pp. 1394–1401 (2018)
Torres, J.F., Troncoso, A., Koprinska, I., Wang, Z., Martínez-Álvarez, F.: Deep learning for big data time series forecasting applied to solar power. In: Grana, M., et al. (eds.) SOCO’18-CISIS’18-ICEUTE’18 2018. AISC, vol. 771, pp. 123–133. Springer, Cham (2019). https://doi.org/10.1007/978-3-319-94120-2_12
Vaswani, A., et al.: Attention is all you need. In: Proceedings of NIPS, pp. 5998–6008 (2017)
Vijesh, V., Drisya, G.V., Kumar, K.S.: Network based periodicity detection of a time series. In: Proceedings of RAICS, pp. 199–203 (2018)
Wang, J., Wang, Z., Li, J., Wu, J.: Multilevel wavelet decomposition network for interpretable time series analysis. In: Proceedings of CIKM, pp. 2437–2446 (2018)
Wang, L., Zhou, L., Xu, G., Li, X.: Date-compensated discrete fourier transform for periodicity detection in unevenly astronomical time series. In: Proceedings of AIPC, vol. 2073 (2019)
Wang, Y., Liu, Z., Hu, D., Zhang, M.: Multivariate time series prediction based on optimized temporal convolutional networks with stacked auto-encoders. In: Proceedings of ACML, pp. 157–172 (2019)
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of AAAI (2018)
Acknowledgments
Funding support for this research was in part provided by Zhejiang Department of Education (No.Y20194137).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, T., Jin, C., Dong, T., Chen, D. (2020). A Deep Time Series Forecasting Method Integrated with Local-Context Sensitive Features. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science(), vol 12534. Springer, Cham. https://doi.org/10.1007/978-3-030-63836-8_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-63836-8_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63835-1
Online ISBN: 978-3-030-63836-8
eBook Packages: Computer ScienceComputer Science (R0)