Abstract
Time series data are widely available in finance, transportation, tourism, and other vital fields and often reflect the dynamic pattern of the observed objects. Scientific and accurate time series forecasting can reduce system operating costs and lower system risk. However, in the era of big data, new forms of data and complex relationships among variables in the data bring significant challenges to traditional forecasting methods. In contrast, artificial intelligence methods can fully mine massive data and thus are widely used in time series forecasting problems. In this paper, machine and deep learning methods are compared and jointly applied to univariate time series prediction scenarios. Experimental results show that deep learning methods outperform machine learning methods in prediction accuracy, but their complex network structures require more training time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Duran, N., Catak, M.: Forecasting of wind speed by means of window-shifted autoregressive time series. In: IEEE 24th Signal Processing and Communication Application Conference (SIU) (2016)
Yasmeen, F., Sharif, M.: Forecasting electricity consumption for Pakistan. Int. J. Emerg. Technol. Adv. Eng. 4(4), 496–503 (2014)
Eljazzar, M.M., Hemayed, E.E.: Enhancing electric load forecasting of ARIMA and ANN using adaptive fourier series. In: IEEE 7th Annual Computing and Communication Workshop and Conference, pp. 1–6 (2017)
Labouar, A., Slama, J.B.H.: Hour-ahead wind power forecast based on random forests. Renew. Energy 109, 529–541 (2017)
Hu, Q., Zhang, S., Xie, Z., et al.: Noise model based v-support vector regression with its application to short-term wind speed forecasting. Neural Netw. 57, 1–11 (2014)
Lin, Y., Huang, X., Chun, W.D., et al.: Early warning for extremely financial risks based on ODR-ADASYN-SVM. J. Manage. Sci. China 19(5), 87–101 (2016). (In Chinese)
Huang, Q., Wei, S.: Improved quantile convolutional neural network with two-stage training for daily-ahead probabilistic forecasting of photovoltaic power. Energy Convers. Manage. 220, 113085 (2020)
Zeroual, A., Harrou, F., Dairi, A., et al.: Deep learning methods for forecasting CoVID-19 time series data: a comparative study. Chaos Solitons Fract. 140, 110121 (2020)
Zhang, P., Ci, B.: Deep belief network for gold price forecasting. Resour. Policy 69, 101806 (2020)
Shi, J., Guo, J., Zheng, S.: Evaluation of hybrid forecasting approaches for wind speed and power generation time series. Renew. Sustain. Energy Rev. 16(5), 3471–3480 (2012)
Hu, J., Wang, J., Zeng, G.: A hybrid forecasting approach applied to wind speed time series. Renew. Energy 32(7), 82–86 (2013)
Darwish, A., Hassanien, A.E., Das, S.: A survey of swarm and evolutionary computing approaches for deep learning. Artif. Intell. Rev. 53(3), 1767–1812 (2020)
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 Singapore Pte Ltd.
About this paper
Cite this paper
He, X. (2023). A Survey on Time Series Forecasting. In: Patnaik, S., Kountchev, R., Tai, Y., Kountcheva, R. (eds) 3D Imaging—Multidimensional Signal Processing and Deep Learning. Smart Innovation, Systems and Technologies, vol 348. Springer, Singapore. https://doi.org/10.1007/978-981-99-1145-5_2
Download citation
DOI: https://doi.org/10.1007/978-981-99-1145-5_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1144-8
Online ISBN: 978-981-99-1145-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)