Table 3.
Sensitivity (true-positive rate, TPR), specificity (true-negative rate, TNR), and accuracy (ACC) for the faller classification using the TUG 6.
| Neurons | Epochs | Regularisation | TUG 6 | ||
|---|---|---|---|---|---|
| TPR | TNR | ACC | |||
| 5 | 2 | false | 72% | 38% | 65% |
| 5 | 2 | true | 81% | 25% | 70% |
| 5 | 4 | false | 91% | 13% | 75% |
| 5 | 4 | true | 97% | 0% | 78% |
| 5 | 20 | false | 91% | 63% | 85% |
| 5 | 20 | true | 100% | 0% | 80% |
| 7 | 2 | false | 84% | 25% | 73% |
| 7 | 2 | true | 75% | 25% | 65% |
| 7 | 4 | false | 97% | 13% | 80% |
| 7 | 4 | true | 97% | 13% | 80% |
| 7 | 20 | false | 91% | 50% | 83% |
| 7 | 20 | true | 100% | 0% | 80% |
| 10 | 2 | false | 69% | 50% | 65% |
| 10 | 2 | true | 57% | 25% | 50% |
| 10 | 4 | false | 94% | 25% | 80% |
| 10 | 4 | true | 97% | 13% | 80% |
| 10 | 20 | false | 91% | 50% | 83% |
| 10 | 20 | true | 100% | 13% | 83% |