Table 8 Decomposition accuracy of ML-DRSNet, ML-DCNN, and MT-DCNN at 10%, 30%, and 50% MVC at their optimal window sizes and step sizes
Intensity | Method | ML-DRSNet | ML-DCNN | MT-DCNN |
|---|---|---|---|---|
10% MVC | Precision | 0.94 ± 0.11 | 1.00 ± 0.00 | 0.96 ± 0.04 |
Sensitivity | 0.82 ± 0.28 | 1.00 ± 0.00 | 0.94 ± 0.04 | |
F1-score | 0.84 ± 0.26 | 1.00 ± 0.00 | 0.95 ± 0.04 | |
Correctly identified MU counts | 12.31 ± 11.57 | 17.06 ± 8.32 | 15.38 ± 8.98 | |
30% MVC | Precision | 0.96 ± 0.07 | 1.00 ± 0.00 | 0.96 ± 0.04 |
Sensitivity | 0.91 ± 0.18 | 1.00 ± 0.00 | 0.92 ± 0.04 | |
F1-score | 0.91 ± 0.17 | 1.00 ± 0.00 | 0.94 ± 0.04 | |
Correctly identified MU counts | 13.81 ± 10.53 | 16.50 ± 7.97 | 13.00 ± 8.29 | |
50% MVC | Precision | 0.89 ± 0.16 | 1.00 ± 0.00 | 0.95 ± 0.04 |
Sensitivity | 0.80 ± 0.26 | 1.00 ± 0.00 | 0.92 ± 0.05 | |
F1-score | 0.81 ± 0.25 | 1.00 ± 0.00 | 0.93 ± 0.04 | |
Correctly identified MU counts | 6.56 ± 8.37 | 10.56 ± 7.17 | 7.31 ± 6.11 |