Skip to main content

Advertisement

SpringerLink
Log in

Using improved gradient-boosted decision tree algorithm based on Kalman filter (GBDT-KF) in time series prediction

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

In this study, we analyse two mobile phone activity datasets to predict the future traffic of mobile base stations in urban areas. The predicted time series can be used to reflect the trend of human activity flow. Although common methods such as recurrent neural network and long short-term memory (LSTM) network often achieve a high precision, they have the short back of time-consuming. So, we present the improved gradient-boosted decision tree algorithm based on Kalman filter (GBDT-KF) due to the noise in the original time series, because the decrease in the performance of GBDT is usually caused by overfitting the noise in the signal. According to our experiments, although the RMSE of the predicted values of our GBDT-KF and the ground truth is only 12–14% worse than that of the LSTM model, the proposed GBDT-KF algorithm makes a trade-off between the precision and time complexity and achieves over 100-time training time reduction compared with the LSTM model. By implementing the result of our work, service providers could predict where and when a network congestion would happen; therefore, they could take actions ahead of time. Such applications are useful especially in the era of 5G.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. China: mobile users 2019 | Statista[EB/OL]. Statista, 2019. (2019)[2019 -12 -16]. https://www.statista.com/statistics/278204/china-mobile-users-by-month/

  2. Lei PR, Shen TJ, Peng WC, Su IJ (2011) Exploring spatial-temporal trajectory model for location prediction. In: IEEE International Conference on Mobile Data Management, pp 58–67

  3. Dong F (2012) When and where next: individual mobility prediction. In: ACM Sigspatial International Workshop on Mobile Geographic Information Systems, pp 57–64

  4. Barlacchi G et al (2015) A multi-source dataset of urban life in the city of Milan and the Province of Trentino. Sci Data 2:150055

    Article  Google Scholar 

  5. Nazaripouya H, Wang B, Wang Y, Chu P, Pota HR, Gadh R (2016) Univariate time series prediction of solar power using a hybrid wavelet-ARMA-NARX prediction method. In: Transmission and Distribution Conference and Exposition, pp 1–5

  6. Gumus B, Kilic H (2018) Time dependent prediction of monthly global solar radiation and sunshine duration using exponentially weighted moving average in southern of Turkey. Therm Sci 22(2):943–951

    Article  Google Scholar 

  7. Engle RF (1982) Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica 50(4):987–1007

    Article  MathSciNet  Google Scholar 

  8. Bollerslevb T (1986) Generalized autoregressive conditional heteroskedasticity. J Econ 31(3):307–327

    Article  MathSciNet  Google Scholar 

  9. Luong MT, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. Computer Science

  10. Graves A (2013) Generating sequences with recurrent neural networks, Computer Science

  11. Cho K et al. (2014) Learning phrase representations using RNN encoder–decoder for statistical machine translation, Computer Science

  12. Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate, Computer Science

  13. Ahmad S, Lavin A, Purdy S et al (2017) Unsupervised real-time anomaly detection for streaming data. Neurocomputing 262:134–147

    Article  Google Scholar 

  14. Gilson M et al. (2019) The covariance perceptron: a new framework for classification and processing of time series in recurrent neural networks. bioRxiv: 562546

  15. Lebret R, Grangier D, Auli M (2016) Neural text generation from structured data with application to the biography domain. In: Conference on Empirical Methods in Natural Language Processing, pp 1203–1213

  16. Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. Preprint https://arxiv.org/1803.01271

  17. Gers F, Eck D (2001) Applying LSTM to time series predictable through time-window approaches. In: International Conference on Artificial Neural Networks, pp 669–676

  18. Tian D, He G, Wu J, Chen H, Jiang Y (2016) An accurate eye pupil localization approach based on adaptive gradient boosting decision tree. In: Visual Communications and Image Processing (VCIP), pp 1–4

  19. Shashank G et al (2018) Semi-supervised recurrent neural network for adverse drug reaction mention extraction. BMC Bioinform 19(8):212

    Google Scholar 

  20. Ghahramani Z, Hinton GE (1996) Parameter estimation for linear dynamical systems

  21. Chai T, Draxler RR (2014) Root mean square error (RMSE) or mean absolute error (MAE)? Geosci Model Dev Discuss 7(3):1247–1250

    Article  Google Scholar 

  22. Ying X, Chen J (2017) Traffic flow forecasting method based on gradient boosting decision tree. In: 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017). Atlantis Press

Download references

Acknowledgements

This work was supported in part by a grant from foundation project for the Science and Technology Department of Jilin Province (Grant No. 20170101140JC).

Author information

Authors and Affiliations

  1. Department of Communication Engineering, Jilin University, Changchun, 130012, China

    Ling Li, Sida Dai & Zhiwei Cao

  2. Northeast Normal University, Changchun, 130032, China

    Jinghui Hong

  3. State Grid Jilin Changchun Power Supply Company, Changchun, 130012, China

    Shu Jiang

  4. High School Attached to Northeast Normal University, Changchun, 130032, China

    Kunmeng Yang

Authors
  1. Ling Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sida Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhiwei Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jinghui Hong
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shu Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kunmeng Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ling Li.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, L., Dai, S., Cao, Z. et al. Using improved gradient-boosted decision tree algorithm based on Kalman filter (GBDT-KF) in time series prediction. J Supercomput 76, 6887–6900 (2020). https://doi.org/10.1007/s11227-019-03130-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-019-03130-y

Keywords

Search

Navigation