Showing 2,141 - 2,160 results of 4,761 for search 'significantly ((((larger decrease) OR (((nn decrease) OR (mean decrease))))) OR (greater decrease))', query time: 0.46s Refine Results
  1. 2141

    Fitting curve parameters. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  2. 2142

    Test instrument. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  3. 2143

    Empirical model establishment process. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  4. 2144

    Model prediction error trend chart. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  5. 2145

    Basic physical parameters of red clay. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  6. 2146

    BP neural network structure diagram. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  7. 2147

    Structure diagram of GBDT model. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  8. 2148

    Model prediction error analysis index. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  9. 2149

    Fitting curve parameter table. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  10. 2150

    Model prediction error analysis. by Hongqi Wang (2208238)

    Published 2024
    “…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”
  11. 2151
  12. 2152

    Complexity comparison of different models. by Li Yuan (102305)

    Published 2025
    “…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”
  13. 2153

    Dynamic window based median filtering algorithm. by Li Yuan (102305)

    Published 2025
    “…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”
  14. 2154

    Flow of operation of improved KMA. by Li Yuan (102305)

    Published 2025
    “…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”
  15. 2155

    Improved DAE based on LSTM. by Li Yuan (102305)

    Published 2025
    “…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”
  16. 2156

    Autoencoder structure. by Li Yuan (102305)

    Published 2025
    “…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”
  17. 2157
  18. 2158
  19. 2159
  20. 2160

    Parameters of screws. by Pilan Jaipanya (12861176)

    Published 2025
    “…For these reasons, surgeons may avoid CPS insertion despite its benefit of greater biomechanical strength. Therefore, an improvement in the CPS design is needed to avoid this catastrophic complication.…”