Comparative performance of different anomaly detection approaches
| Model/Approach | Accuracy (%) | Anomaly recall (%) | Physical interpretability | Industrial applicability |
|---|---|---|---|---|
| Whole-file Averaging + XGBoost | 81.3 | 72.7 | Low | Limited |
| Support Vector Machine (SVM) | 85.4 | 81.8 | Low | Moderate |
| Random Forest (RF) | 87.5 | 90.9 | Medium | Good |
| XGBoost without UDI | 91.6 | 90.9 | Medium | Good |
| Proposed Interval-wise UDI + XGBoost + SHAP | 93.75 | 100.0 | High | Very High |
| Model/Approach | Accuracy (%) | Anomaly recall (%) | Physical interpretability | Industrial applicability |
|---|---|---|---|---|
| Whole-file Averaging + XGBoost | 81.3 | 72.7 | Low | Limited |
| Support Vector Machine (SVM) | 85.4 | 81.8 | Low | Moderate |
| Random Forest (RF) | 90.9 | Medium | Good | |
| XGBoost without UDI | 91.6 | 90.9 | Medium | Good |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.