Fig 1.
Architecture diagram of the principal component analysis (PCA)-enhanced RVFLNs algorithm (P-RVFLNs).
Fig 2.
Structure of the PSO-P-ERVFLNs (an RVFLNs ensemble modeling method integrating PCA and PSO) Algorithm.
Table 1.
Dataset Feature Descriptions.
Fig 3.
(A) presents histograms of four features—V2, V3, V7, and V8—that contained more captured outliers. As shown in (A), the effectiveness of the IQR method in detecting data outliers can be more clearly and intuitively illustrated. (B) provides a clear statistical analysis of the dataset. These data processing methods improve the accuracy of data analysis and provide a reliable foundation for subsequent modeling.
Table 2.
Results of the Feature Optimization.
Fig 4.
Histogram of Statistical Analysis of the Dataset after Feature Selection by the Random Forest Algorithm.
Fig 5.
Sensitivity Analysis of Hidden Layer Node Count.
Curve of RMSE versus Number of Hidden Layer Nodes for RVFLNs and P-RVFLNs Sub-learners with Different Activation Functions.
Fig 6.
Modeling Effect Comparison Chart.
(A) Performance of each sub-model. (B) Performance of the ensemble model. (C) Comparative analysis of model error curves.
Fig 7.
Results of the SHapley Additive exPlanations (SHAP) Model Analysis.
(A) Reflects the overall impact intensity of each parameter on the model output; the higher the value, the greater the impact. (B) Shows the distribution of SHAP values for each parameter, indicating the direction and range of each parameter’s influence on the prediction results; the magnitude reflects the strength of the positive contribution.
Table 3.
Results of Ten-Fold Cross-Validation and Sensitivity Analysis.
Table 4.
Details of Model Parameters and Performance Evaluation Results for Baijiu Yield Prediction with Different Algorithms.
Fig 8.
Prediction Results of Baijiu Yield Modeling with Different Algorithms.