Showing 3,481 - 3,500 results of 21,342 for search '(( significant decrease decrease ) OR ( significant ((threat decrease) OR (larger decrease)) ))', query time: 0.55s Refine Results
  1. 3481

    LOSS curves for BWO-BiLSTM model training. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  2. 3482

    Analysis of STL-PCA prediction results. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  3. 3483

    Accumulated contribution rate of PCA. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  4. 3484

    Figure of ablation experiment. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  5. 3485

    Flowchart of the STL-PCA-BWO-BiLSTM model. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  6. 3486

    Parameter optimization results of BiLSTM. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  7. 3487

    Descriptive statistical analysis of data. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  8. 3488

    The MAE value of the model under raw data. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  9. 3489

    Three error values under raw data. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  10. 3490

    Decomposition of time scries plot. by Xiangjuan Liu (618000)

    Published 2025
    “…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”
  11. 3491

    Achieving Improved Ion Swarm Shaping Based on Ion Leakage Control in Ion Mobility Spectrometry by Jiyao Wang (2121157)

    Published 2025
    “…In Ion Mobility Spectrometry (IMS), ion gates are essential for controlling ion flow, significantly impacting detection sensitivity and resolution. …”
  12. 3492
  13. 3493
  14. 3494
  15. 3495
  16. 3496
  17. 3497
  18. 3498
  19. 3499
  20. 3500