يعرض 3,421 - 3,440 نتائج من 21,342 نتيجة بحث عن '(( significant decrease decrease ) OR ( significant ((non decrease) OR (a decrease)) ))*', وقت الاستعلام: 0.80s تنقيح النتائج
  1. 3421
  2. 3422
  3. 3423
  4. 3424
  5. 3425
  6. 3426
  7. 3427
  8. 3428
  9. 3429
  10. 3430
  11. 3431

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

    منشور في 2025
    "…Simulations and experiments demonstrate that precise voltage adjustments effectively minimize ion leakage, enhancing resolving power by 50% (reaching a maximum of 106), while the corresponding decrease in signal intensity follows the <i>I</i><sub>p</sub>–<i>R</i><sub>p</sub> linear relationship. …"
  12. 3432
  13. 3433

    Testing set error. حسب Xiangjuan Liu (618000)

    منشور في 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. …"
  14. 3434

    Internal structure of an LSTM cell. حسب Xiangjuan Liu (618000)

    منشور في 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. …"
  15. 3435

    Prediction effect of each model after STL. حسب Xiangjuan Liu (618000)

    منشور في 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. …"
  16. 3436

    The kernel density plot for data of each feature. حسب Xiangjuan Liu (618000)

    منشور في 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. …"
  17. 3437

    Analysis of raw data prediction results. حسب Xiangjuan Liu (618000)

    منشور في 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. …"
  18. 3438

    Flowchart of the STL. حسب Xiangjuan Liu (618000)

    منشور في 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. …"
  19. 3439

    SARIMA predicts season components. حسب Xiangjuan Liu (618000)

    منشور في 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. …"
  20. 3440

    BWO-BiLSTM model prediction results. حسب Xiangjuan Liu (618000)

    منشور في 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. …"