The test results of swelling pressure of reinforced expansive soil. حسب Yonggang Huang (223155)

الموضوعات:

Sampling point (Source: حسب Yonggang Huang (223155)

الموضوعات:

Enrichment Analysis Based on Ferroptosis-Related Differentially Expressed Genes. حسب Jiyong Zhang (2498740)

الموضوعات:

Correlation between hub genes and 50 hallmark signaling pathways. حسب Jiyong Zhang (2498740)

الموضوعات:

ROC curves for hub genes. حسب Jiyong Zhang (2498740)

الموضوعات:

Intersection genes obtained from the PPI network and PPI network analysis of intersection genes. colored circles represent genes. حسب Jiyong Zhang (2498740)

الموضوعات:

Expression profile heatmaps of key genes in gene sets. حسب Jiyong Zhang (2498740)

الموضوعات:

Influence of UHMWPE length on free swelling ratio. حسب Yonggang Huang (223155)

الموضوعات:

Construction of the WGCNA Co-expression Network. حسب Jiyong Zhang (2498740)

الموضوعات:

Influence of UHMWPE content on free swelling ratio. حسب Yonggang Huang (223155)

الموضوعات:

Differential Gene Expression Associated with Non-Alcoholic Fatty Liver Disease. حسب Jiyong Zhang (2498740)

الموضوعات:

Interaction analysis of hub genes. حسب Jiyong Zhang (2498740)

الموضوعات:

Sphingolipid biosynthetic pathway. حسب Hala Tamim El Jarkass (16625309)

الموضوعات:

Testing set error. حسب Xiangjuan Liu (618000)

"…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. …"

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

"…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. …"

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

"…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. …"

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

"…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. …"

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

"…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. …"

Flowchart of the STL. حسب Xiangjuan Liu (618000)

"…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. …"

SARIMA predicts season components. حسب Xiangjuan Liu (618000)

"…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. …"