Journal of Electronic Science and Technology, Volume. 22, Issue 2, 100256(2024)

CNN-LSTM based incremental attention mechanism enabled phase-space reconstruction for chaotic time series prediction

Xiao-Qian Lu1... Jun Tian2,*, Qiang Liao2, Zheng-Wu Xu3 and Lu Gan3 |Show fewer author(s)
Author Affiliations
  • 1Bidding and Purchasing Center, University of Electronic Science and Technology of China, Chengdu, 611731, China
  • 2Yibin Research Institute, University of Electronic Science and Technology of China, Yibin, 644000, China
  • 3School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China
  • show less
    Figures & Tables(20)
    Overall network structure.
    Prediction model of IAN.
    One-dimensional convolutional neural network.
    Network structure of LSTM.
    Prediction of the logistic system.
    Prediction of the Lorenz system.
    Prediction of the sunspot series.
    • Table 1. Parameters estimation algorithm.

      View table
      View in Article

      Table 1. Parameters estimation algorithm.

      Algorithm: Parameter estimation algorithm
      Input: $\rm{all} \; (m{\mathrm{,}}\; \tau) $
      Output: $\rm{best} \; (m{\mathrm{,}}\; \tau) $
      1: Initialize: Set $m_0=1{\mathrm{,}}\; \tau_0=0 $
      2: for $ m=1{\mathrm{,}}\; 2{\mathrm{,}}\; \cdots{\mathrm{,}}\; m_{{\mathrm{max}} } $ do
      3:  for $\tau=0{\mathrm{,}}\;1{\mathrm{,}}\; \cdots{\mathrm{,}}\; \tau_{{\mathrm{max}} } $ do
      4:  if $(m{\mathrm{,}}\; \tau) $ fit DWC then save;
      5:   else continue;
      6:   end if
      7:  end for
      8: end for
    • Table 2. Phase space reconstruction parameters of logistic system.

      View table
      View in Article

      Table 2. Phase space reconstruction parameters of logistic system.

      MethodEmbedding dimensionDelay
      IAN25
      CAO59
      FNN415
      C-C123
    • Table 3. Dimension contribution weight of the logistic system.

      View table
      View in Article

      Table 3. Dimension contribution weight of the logistic system.

      DimensionContribution weightIncremental
      1[1.0]Yes
      2[0.3808, 0.6192]Yes
      3[0.2507, 0.4120, 0.3384 ]No
      4[0.2430, 0.1731, 0.3057, 0.2782]No
    • Table 4. Predicted RMSE error table of the logistic system.

      View table
      View in Article

      Table 4. Predicted RMSE error table of the logistic system.

      ModelIANCAOFNNC-C
      CNN-LSTM0.00610.00840.00870.0072
      LSTM0.00690.01880.00840.0103
      CNN0.00870.01380.01150.0907
      SVR0.04990.06640.05160.0873
      RNN0.01460.02770.04370.0298
    • Table 5. Predicted MAE error table of the logistic system.

      View table
      View in Article

      Table 5. Predicted MAE error table of the logistic system.

      ModelIANCAOFNNC-C
      CNN-LSTM0.000250.000340.000360.00029
      LSTM0.000280.000770.000340.00042
      CNN0.000360.000560.000470.00370
      SVR0.002040.002710.002110.00356
      RNN0.000600.001130.001780.00122
    • Table 6. Phase space reconstruction parameters of the Lorenz system.

      View table
      View in Article

      Table 6. Phase space reconstruction parameters of the Lorenz system.

      MethodEmbedding dimensionDelay
      IAN36
      CAO717
      FNN517
      C-C610
    • Table 7. Dimension contribution weight of the Lorenz system.

      View table
      View in Article

      Table 7. Dimension contribution weight of the Lorenz system.

      DimensionContribution weightIncremental
      1[1.0]Yes
      2[0.01051, 0.98949]Yes
      3[0.1748, 0.2845, 0.5427]Yes
      4[0.1911, 0.2078, 0.3186, 0.2825]No
      5[0.1689, 0.2367, 0.1999, 0.2808, 0.1136]No
    • Table 8. Predicted RMSE error table of the Lorenz system.

      View table
      View in Article

      Table 8. Predicted RMSE error table of the Lorenz system.

      ModelIANCAOFNNC-C
      CNN-LSTM0.12640.33060.28010.2393
      LSTMs0.13310.22790.25110.1857
      CNN0.14910.30620.46270.6170
      SVR1.78392.17782.13051.9869
      RNN0.13520.37090.31060.3161
    • Table 9. Predicted MAE error table of the Lorenz system.

      View table
      View in Article

      Table 9. Predicted MAE error table of the Lorenz system.

      ModelIANCAOFNNC-C
      CNN-LSTM0.005160.013500.011440.00977
      LSTM0.005430.009300.010250.00758
      CNN0.006090.012500.018890.02519
      SVR0.072830.088910.086980.08111
      RNN0.005520.015140.012680.01290
    • Table 10. Phase space reconstruction parameters of the sunspot series.

      View table
      View in Article

      Table 10. Phase space reconstruction parameters of the sunspot series.

      MethodEmbedding dimensionDelay (month)
      IAN53
      CAO1214
      FNN514
      C-C327
    • Table 11. Dimension contribution weight of the sunspot series.

      View table
      View in Article

      Table 11. Dimension contribution weight of the sunspot series.

      DimensionContribution weightIncremental
      1[1.0]No
      2[0.4175, 0.5825]Yes
      3[0.2307, 0.2431, 0.5263]Yes
      4[0.1751, 0.2042, 0.2757, 0.3450]Yes
      5[0.0180, 0.0587, 0.1143, 0.2405, 0.5685]Yes
      6[0.2109, 0.1194, 0.1376, 0.1675, 0.1984, 0.1662]No
      7[0.1173, 0.2157, 0.1516, 0.1115, 0.1474, 0.1319, 0.1245]No
    • Table 12. Predicted RMSE error table of the sunspot series.

      View table
      View in Article

      Table 12. Predicted RMSE error table of the sunspot series.

      ModelIANCAOFNNC-C
      CNN-LSTM25.600328.753533.989130.2471
      LSTMs25.904525.992726.514326.8429
      CNN25.793228.182426.291326.5868
      SVR30.266332.517132.118530.5299
      RNN25.766225.898426.587126.6672
    • Table 13. Predicted MAE error table of the sunspot series.

      View table
      View in Article

      Table 13. Predicted MAE error table of the sunspot series.

      ModelIANCAOFNNC-C
      CNN-LSTM1.045131.173861.387601.23483
      LSTM1.057551.061151.082441.09586
      CNN1.053001.150541.073341.08540
      SVR1.235621.327511.311231.24638
      RNN1.051901.057301.085411.08868
    Tools

    Get Citation

    Copy Citation Text

    Xiao-Qian Lu, Jun Tian, Qiang Liao, Zheng-Wu Xu, Lu Gan. CNN-LSTM based incremental attention mechanism enabled phase-space reconstruction for chaotic time series prediction[J]. Journal of Electronic Science and Technology, 2024, 22(2): 100256

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: Dec. 23, 2023

    Accepted: Apr. 22, 2024

    Published Online: Aug. 8, 2024

    The Author Email: Tian Jun (uestctj@gmail.com)

    DOI:10.1016/j.jnlest.2024.100256

    Topics