Table 4.
Summary of performance metrics for classification models that gave the best results for each computational approach (i.e., sensory-based, spectral-based, and data-fusion-based).
| Type of Model | Features | Matrix Type | Model Acronym | LVs | Captured Variance (%) | Sensitivity | Specificity | Accuracy | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| X-Block | Y-Block | CA 1 | CV 2 | CA | CV | CA | CV | |||||
| Sensory based | 5 | Raw | Sr | 3 | 87.34 | 84.37 | 0.96 | 0.96 | 0.98 | 0.98 | 0.97 | 0.97 |
| Boiled | Sb | 3 | 89.93 | 76.84 | 0.95 | 0.94 | 0.95 | 0.96 | 0.95 | 0.95 | ||
| Spectral based | 3112 | Raw | Nr | 3 | 99.39 | 89.90 | 0.99 | 0.98 | 0.97 | 0.98 | 0.98 | 0.98 |
| Boiled | Nb | 3 | 99.53 | 34.91 | 0.90 | 0.82 | 0.80 | 0.74 | 0.85 | 0.78 | ||
| Data fusion based | 3117 | Raw | Fr | 3 | 99.28 | 90.03 | 0.99 | 0.98 | 1.00 | 0.99 | 1.00 | 0.99 |
| Boiled | Fb | 7 | 99.93 | 84.40 | 0.98 | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | ||
1 CA, Calibration. 2 CV, Cross-validation.