Generic placeholder image

Recent Advances in Computer Science and Communications

Author(s): Danyang Cao, Jinfeng Ma, Ling Sun* and Nan Ma

DOI: 10.2174/2666255815666220316154957

DownloadDownload PDF Flyer Cite As
A Time-series Prediction Algorithm Based on a Hybrid Model

Article ID: e160322202292 Pages: 15

  • * (Excluding Mailing and Handling)

Explore Articles
About Journal
For Authors
For Editors
For Reviewers

Abstract

Background: In reality, time series is composed of several basic components, which have linear, nonlinear and non-stationary characteristics at the same time. Directly using a single model will show some limitations and the prediction accuracy is difficult to improve.

Methods: We propose a mixed forecasting model based on time series decomposition, namely STL-EEMD-LSTM model. First, we use STL filtering algorithm to decompose the time series to obtain the trend component, seasonal component and the remainder component of the time series; then we use EEMD to decompose the seasonal component and the remainder component to obtain multiple sub-sequences. After this, we reconstruct the new seasonal component and the remainder component according to the fluctuation frequency of the sub-sequence. Finally, we use LSTM to build a prediction model for each component obtained by decomposition.

Results: We applied the proposed model to simulation data and the time series of satellite calibration parameters and found that the hybrid prediction model proposed in this paper has high prediction accuracy.

Conclusion: Therefore, we believe that our proposed model is more suitable for the prediction of time series with complex components.

Keywords: STL, EEMD, LSTM, time series decomposition, time series forecasting, calibration parameter.

Graphical Abstract

[1]
Yu Qiong, and Tian Xian, "Nonlinear time series prediction algorithm based on combined model", Comput. Eng. Sci., vol. 43, no. 10, pp. 1817-1825, 2021.
[2]
Y. Hong, Y. Yang, K. Yu, and A. Hu, "Japan’s relative GDP and positions in services trade: Co-integration and granger causality tests based on linear VEC models", In: FEBM, 2019, pp. 249-252.
[3]
L. Wen, W. Jian, L. Fei, and Liu Xu, "Research on GNSS/accelerometer vibration monitoring model based on EMD", Geod. Geodyn., vol. 41, no. 12, pp. 1306-1311, 2021.
[4]
T. Li, and M. Zhou, "ECG classification using wavelet packet entropy and random forests", Entropy (Basel), vol. 18, p. 285, 2016.
[http://dx.doi.org/10.3390/e18080285]
[5]
G. Zhang, H. Zhou, C. Wang, H. Xue, J. Wang, and H. Wan, "Forecasting time series albedo using NARnet based on EEMD decomposition", IEEE Trans. Geosci. Remote Sens., vol. 58, no. 5, pp. 3544-3557, 2020.
[http://dx.doi.org/10.1109/TGRS.2019.2958048]
[6]
W. Deng, S. Zhang, H. Zhao, and X. Yang, "A novel fault diagnosis method based on integrating empirical wavelet transform and fuzzy entropy for motor bearing", IEEE Access, vol. 6, pp. 35042-35056, 2018.
[http://dx.doi.org/10.1109/ACCESS.2018.2834540]
[7]
H. Zhao, S. Meng, W. Deng, and X. Yang, "A new feature extraction method based on EEMD and multi-scale fuzzy entropy for motor bearing", Entropy (Basel), vol. 19, p. 14, 2017.
[http://dx.doi.org/10.3390/e19010014]
[8]
B. Zhu, X. Shi, J. Chevallier, P. Wang, and Y.M. Wei, "An adaptive multiscale ensemble learning paradigm for nonstationary and nonlinear energy price time series forecasting", J. Forecast., vol. 35, pp. 633-651, 2016.
[http://dx.doi.org/10.1002/for.2395]
[9]
L. Tang, W. Dai, L. Yu, and S. Wang, "A novel CEEMD-based EELM ensemble learning paradigm for crude oil price forecasting", Int. J. Inf. Technol. Decis. Mak, vol. 14, pp. 141-169, 2015.
[http://dx.doi.org/10.1142/S0219622015400015]
[10]
J. Huan, W. Cao, and Y. Qin, "Prediction of dissolved oxygen in aquaculture based on EEMD and LSSVM optimized by the Bayesian evidence framework", Comput. Electron. Agric., vol. 150, pp. 257-265, 2018.
[http://dx.doi.org/10.1016/j.compag.2018.04.022]
[11]
Y. Zhou, T. Li, J. Shi, and Z. A Qian, "Ceemdan and XGBOOSTbased approach to forecast crude oil prices", Complexity, vol. 2019, 2019.
[12]
L. Xu, and W. Jian, "Li Wen Structural vibration time-frequency extraction model integrating variational modal decomposition and Hilbert Huang transform", J. Wuhan Univ., vol. 46, no. 11, pp. 1686-1692, 2021.
[http://dx.doi.org/10.13203/j.whugis20200646]
[13]
H. Zheng, J. Yuan, and L. Chen, "Short-term load forecasting using EMD-LSTM neural networks with a xgboost algorithm for feature importance evaluation", Energies, vol. 10, p. 1168, 2017.
[http://dx.doi.org/10.3390/en10081168]
[14]
B. Zhu, S. Ye, P. Wang, K. He, T. Zhang, and Y.M. Wei, "A novel multiscale nonlinear ensemble leaning paradigm for carbon price forecasting", Energy Econ., vol. 70, pp. 143-157, 2018.
[http://dx.doi.org/10.1016/j.eneco.2017.12.030]
[15]
G.F. Fan, L.L. Peng, W.C. Hong, and F. Sun, "Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression", Neurocomputing, vol. 173, pp. 958-970, 2016.
[http://dx.doi.org/10.1016/j.neucom.2015.08.051]
[16]
J.L. Zhang, Y.J. Zhang, and L. Zhang, "A novel hybrid method for crude oil price forecasting", Energy Econ., vol. 49, pp. 649-659, 2015.
[http://dx.doi.org/10.1016/j.eneco.2015.02.018]
[17]
W. Bao, J. Yue, and Y. Rao, "A deep learning framework for financial time series using stacked autoencoders and long-short term memory", PLoS One, vol. 12, no. 7, p. e0180944, 2017.
[http://dx.doi.org/10.1371/journal.pone.0180944] [PMID: 28708865]
[18]
L. Bei, and R. Dong, "Research on GNSS water vapor prediction based on wavelet transform and RBF neural network", Geodesy Geodynam., vol. 41, no. 12, pp. 1216-1218, 2021.
[19]
J. Hu, Y. Fu, J. Kang, Z. Qi, and X. Wang, "An improved mean filtering algorithm in wavelet domain", Surv. Map. Sci., vol. 46, no. 09, pp. 55-60, 2021.
[20]
J. Wang, and J. Wang, "Forecasting stochastic neural network based on financial empirical mode decomposition", Neural Netw., vol. 90, pp. 8-20, 2017.
[http://dx.doi.org/10.1016/j.neunet.2017.03.004] [PMID: 28364677]
[21]
R. Bisoi, P.K. Dash, and A.K. Parida, "Hybrid variational mode decomposition and evolutionary robust kernel extreme learning machine for stock price and movement prediction on daily basis", Appl. Soft Comput., vol. 74, pp. 652-678, 2019.
[http://dx.doi.org/10.1016/j.asoc.2018.11.008]
[22]
A.M. Awajan, M.T. Ismail, and S. Al Wadi, "Improving forecasting accuracy for stock market data using EMD-HW bagging", PLoS One, vol. 13, no. 7, p. e0199582, 2018.
[http://dx.doi.org/10.1371/journal.pone.0199582] [PMID: 30016323]
[23]
A.M. Awajan, and M.T. Ismail, "A hybrid approach EMD-HW for short-term forecasting of daily stock market time series data", In Proceedings of the 24th National Symposium on Mathematical Sciences (SKSM), 2017.
[http://dx.doi.org/10.1063/1.4995933]
[24]
H.F. Li, "Price forecasting of stock index futures based on a new hybrid EMDRBF neural network model", Agro Food Ind. Hi-Tech, vol. 28, no. 1, pp. 1744-1747, 2017.
[25]
L.Y. Wei, "A hybrid ANFIS model based on empirical mode decomposition for stock time series forecasting", Appl. Soft Comput., vol. 42, pp. 368-376, 2016.
[http://dx.doi.org/10.1016/j.asoc.2016.01.027]
[26]
Y. Xiu, and X.Y. Chen, "Study on prediction of the shanghai composite index based on EMD and NARX neural network", Proceedings of the 2nd International Conference on Information Technology and Intelligent Transportation Systems (ITITS), 2017, pp. 590-596.
[27]
R.X. Yang, J.Y. He, M.Y. Xu, H.Q. Ni, P. Jones, and N. Samatova, "An intelligent and hybrid weighted fuzzy time series model based on empirical mode decomposition for financial markets forecasting", Adv. Data Mining: Appl. Theor. Aspects., vol. 10933, pp. 104-118, 2018.
[http://dx.doi.org/10.1007/978-3-319-95786-9_8]
[28]
N.N. Zhang, A.J. Lin, and P.J. Shang, "Multidimensional k-nearest neighbor model based on EEMD for financial time series forecasting", Physic-Stat. Mech. Appli., vol. 477, pp. 161-173, 2017.
[http://dx.doi.org/10.1016/j.physa.2017.02.072]
[29]
P. Du, J.Z. Wang, W.D. Yang, and T. Niu, "A novel hybrid model for short-term wind power forecasting", Appl. Soft Comput., vol. 80, pp. 93-106, 2019.
[http://dx.doi.org/10.1016/j.asoc.2019.03.035]
[30]
P. Jiang, Y. Wang, and J. Wang, "Short-term wind speed forecasting using a hybrid model", Energy, vol. 119, pp. 561-577, 2017.
[http://dx.doi.org/10.1016/j.energy.2016.10.040]
[31]
Y. Jiang, G. Huang, X. Peng, Y. Li, and Q. Yang, "A novel wind speed prediction method: Hybrid of correlation-aided DWT, LSSVM and GARCH", J. Wind Eng. Ind. Aerodyn., vol. 174, pp. 28-38, 2018.
[http://dx.doi.org/10.1016/j.jweia.2017.12.019]
[32]
S.W. Fei, "A hybrid model of EMD and multiple-kernel RVR algorithm for wind speed prediction", Int. J. Electr. Power Energy Syst., vol. 78, pp. 910-915, 2016.
[http://dx.doi.org/10.1016/j.ijepes.2015.11.116]
[33]
A. Khosravi, R. Koury, L. Machado, and J. Pabon, "Prediction of wind speed and wind direction using artificial neural network, support vector regression and adaptive neuro-fuzzy inference system", Sustain. Energy Technol. Assess., vol. 25, pp. 146-160, 2018.
[http://dx.doi.org/10.1016/j.seta.2018.01.001]
[34]
Q. Wu, and H.X. Lin, "Short-term wind speed forecasting based on hybrid variational mode decomposition and least squares support vector machine optimized by bat algorithm model", Sustainability, vol. 11, p. 652, 2019.
[http://dx.doi.org/10.3390/su11030652]
[35]
Y. Jiang, G. Huang, Q. Yang, Z. Yan, and C. Zhang, "A novel probabilistic wind speed prediction approach using real time refined", Energy Convers. Manage., vol. 185, pp. 758-773, 2019.
[http://dx.doi.org/10.1016/j.enconman.2019.02.028]
[36]
C. Tian, Y. Hao, and J. Hu, "A novel wind speed forecasting system based on hybrid data preprocessing and multi-objective optimization", Appl. Energy, vol. 231, pp. 301-319, 2018.
[http://dx.doi.org/10.1016/j.apenergy.2018.09.012]
[37]
H. Yin, Z. Dong, Y. Chen, J. Ge, L.L. Lai, A. Vaccaro, and A. Meng, "An effective secondary decomposition approach for wind power forecasting using extreme learning machine trained by crisscross optimization", Energy Convers. Manage., vol. 150, pp. 108-121, 2017.
[http://dx.doi.org/10.1016/j.enconman.2017.08.014]
[38]
M.F. Niu, S.L. Sun, J. Wu, and Y.L. Zhang, "Short-term wind speed hybrid forecasting model based on bias correcting study and its application", In: Math. Probl. Eng, vol. 2015. 2015.
[http://dx.doi.org/10.1155/2015/351354]
[39]
P. Wang, Y. Liu, Z. Qin, and G. Zhang, "A novel hybrid forecasting model for PM₁₀ and SO₂ daily concentrations", Sci. Total Environ., vol. 505, pp. 1202-1212, 2015.
[http://dx.doi.org/10.1016/j.scitotenv.2014.10.078] [PMID: 25461118]
[40]
H.D. He, W.Z. Lu, and Y. Xue, "Prediction of particulate matter at street level using artificial neural networks coupling with chaotic particle swarm optimization algorithm", Build. Environ., vol. 78, pp. 111-117, 2014.
[http://dx.doi.org/10.1016/j.buildenv.2014.04.011]
[41]
Q. Zhou, H. Jiang, J. Wang, and J. Zhou, "A hybrid model for PM₂.₅ forecasting based on ensemble empirical mode decomposition and a general regression neural network", Sci. Total Environ., vol. 496, pp. 264-274, 2014.
[http://dx.doi.org/10.1016/j.scitotenv.2014.07.051] [PMID: 25089688]
[42]
S.S. Qin, F. Liu, J.Z. Wang, and B.B. Sun, "Analysis and forecasting of the particulate matter (PM) concentration levels over four major cities of China using hybrid models", Atmos. Environ., vol. 98, pp. 665-675, 2014.
[http://dx.doi.org/10.1016/j.atmosenv.2014.09.046]
[43]
M.F. Niu, Y.F. Wang, S.L. Sun, and Y.W. Li, "A novel hybrid decomposition-and ensemble model based on CEEMD and GWO for short-term PM2.5 concentration forecasting", Atmos. Environ., vol. 134, pp. 168-180, 2016.
[http://dx.doi.org/10.1016/j.atmosenv.2016.03.056]
[44]
J. Wang, Z. Wang, J. Li, and J. Wu, "Multilevel wavelet decomposition network for interpretable time series analysis", arxiv: 1806.08946..
Available from:https://arxiv.org/abs/1806.08946 [http://dx.doi.org/10.1145/3219819.3220060]