Table 2.
Performance evaluation for discrimination of ultrasonographic tasks. Values are mean and standard deviation computed over the five-fold cross-validation rounds.
| Extracted Features | Learning Method | Accuracy Brain | Accuracy Heart | Overall Accuracy |
|---|---|---|---|---|
| Temporal | SVM | 0.44 ± 0.05 | 0.67 ± 0.02 | 0.60 ± 0.03 |
| Spectral | SVM | 0.45 ± 0.07 | 0.70 ± 0.06 | 0.62 ± 0.03 |
| Time-Frequency | SVM | 0.59 ± 0.04 | 0.83 ± 0.02 | 0.75 ± 0.02 |
| TEPR Sequence | 1D CNN | 0.84 ± 0.17 | 0.96 ± 0.06 | 0.87 ± 0.10 |
| Scalogram | ResNet18 2D CNN | 0.64 ± 0.15 | 0.58 ± 0.10 | 0.60 ± 0.03 |