Model A: Logistic structural model. by Abigail A. Lee (19935335)

“…There was a slight correlation between political ideology with more conservative leanings predicting lower vaccine hesitancy. Additionally, higher income slightly predicted decreased HPV vaccine hesitancy. …”

Sodium levels in Canadian restaurant menu items compared to UK National Salt Reduction Initiative (NSRI) targets by UK NSRI food category. by Caroline G. Middleton (22041479)

Subjects:

Changes in sodium levels, serving sizes, and calories in matched restaurant menu items (2016–2020) by sodium reduction or increase. by Caroline G. Middleton (22041479)

Subjects:

Sodium level changes in matched restaurant menu items (2016–2020) by UK NSRI food category. by Caroline G. Middleton (22041479)

Subjects:

Sodium levels (mg/100 g) in matched restaurant menu items in 2016 and 2020 by UK NSRI food categories with ≥ 10 items. by Caroline G. Middleton (22041479)

Subjects:

Data Sheet 1_Prehospital tranexamic acid decreases early mortality in trauma patients: a systematic review and meta-analysis.docx by Yi Li (1144)

“…</p>Conclusion<p>Prehospital TXA decreases early (24-h) mortality in trauma patients without a significant increase in the risk of VTE and other complications, and further studies are still needed to improve and optimize its management strategy.…”

Correlation degree between carbon emissions per kilometer and various factors. by Jianping Gao (1709425)

Data Sheet 1_Social success in a noisy world: exploring the relationship between decreased sound tolerance and social profiles.pdf by Ashleigh Wickie (21408611)

“…Individual differences in sensory processing may have significant effects on an individual’s capacity to navigate social settings and may influence the development and expression of social competence. …”

Image1_Association between mental health and male fertility: depression, rather than anxiety, is linked to decreased semen quality.tif by Yi Zhang (9093)

“…</p>Results<p>Status of depression was negatively associated with semen quality parameters, whereas no statistically significant association was recognized between anxiety and semen quality except that sperm concentration was decreased by 25.60 (95% CI, 1.226 to 49.965, P=0.040) ×10⁶/ml in moderate to severe anxiety group referring to normal group. …”

<b>The loss of insulin-positive cell clusters precedes the decrease of islet frequency and beta cell area in type 1 diabetes</b> by Denise M. Drotar (21679539)

“…Moreover, changes in endocrine composition also occurred in mAAb+ donors, including a significant decrease in the INS+ islet fraction. These data suggest preferential loss of INS+ small endocrine objects early in type 1 diabetes development.…”

LncRNA <i>C5orf64</i> polymorphisms (rs12518552 and rs2950218) decreases pulmonary tuberculosis susceptibility by Shilin Xu (1884217)

Data Sheet 1_Decreased brain-derived neurotrophic factor expression in chronic kidney disease: integrated clinical and experimental evidence.docx by Juan Chen (61123)

“…</p>Conclusion<p>This study integrated meta-analysis, murine model validation, and single-cell transcriptomic profiling to demonstrate a significant reduction of BDNF in CKD. Furthermore, renal BDNF expression decreased locally, predominantly originating from proximal tubule cells, macrophages, and podocytes, possibly epigenetically inhibited by the upregulation of lnc RNA Bdnf-as.…”

Conditional ablation of <i>Ybx1</i> leads to a reduction in cortical progenitor cell pool and a decrease in cortical thickness. by Jian Zhang (1682)

Testing set error. by Xiangjuan Liu (618000)

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

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

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

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

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

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

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

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

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

Flowchart of the STL. by Xiangjuan Liu (618000)

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

SARIMA predicts season components. by Xiangjuan Liu (618000)

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”