Table 1.
Percentage of correct decisions for the healthy structure and the structure with Damage 1, 2 and 3, for the twenty different machine learning strategies (aluminum plate).
| Machine Name | Healthy | Damage 1 | Damage 2 | Damage 3 |
|---|---|---|---|---|
| Medium Tree | 66% | 76% | 70% | 56% |
| Simple Tree | 64% | 60% | 30% | 58% |
| Complex Tree | 72% | 76% | 58% | 56% |
| Linear SMV | 70% | 60% | 26% | 60% |
| Quadratic SVM | 78% | 70% | 56% | 70% |
| Cubic SVM | 86% | 68% | 66% | 72% |
| Fine Gaussian SVM | 90% | 80% | 66% | 78% |
| Medium Gaussian SVM | 76% | 80% | 56% | 74% |
| Coarse Gaussian SVM | 94% | 64% | 14% | 38% |
| Fine k-NN | 94% | 78% | 74% | 80% |
| Medium k-NN | 80% | 62% | 64% | 74% |
| Coarse k-NN | 94% | 42% | 2% | 24% |
| Cosine k-NN | 84% | 58% | 78% | 72% |
| Cubic k-NN | 80% | 64% | 62% | 76% |
| Weighted k-NN | 94% | 66% | 68% | 80% |
| Boosted Trees | 96% | 0% | 42% | 42% |
| Bagged Trees | 84% | 70% | 66% | 78% |
| Subspace Discriminant | 56% | 44% | 32% | 46% |
| Subspace k-NN | 94% | 78% | 72% | 80% |
| Rusboosted Trees | 98% | 0% | 42% | 0% |