Table 10 Decomposition accuracy of ML-DRSNet, ML-DCNN, and MT-DCNN at 10%, 30%, and 50% MVC at a window size of 20 data points and a step size of 10 data points

10% MVC

Precision

0.92 ± 0.18

0.84 ± 0.16

0.74 ± 0.17

Sensitivity

0.90 ± 0.23

0.67 ± 0.28

0.56 ± 0.18

F1-score

0.90 ± 0.23

0.71 ± 0.25

0.62 ± 0.18

Correctly identified MU counts

15.56 ± 8.67

5.63 ± 5.41

2.00 ± 2.07

30% MVC

Precision

0.84 ± 0.18

0.60 ± 0.22

0.65 ± 0.14

Sensitivity

0.64 ± 0.30

0.32 ± 0.22

0.41 ± 0.11

F1-score

0.68 ± 0.28

0.36 ± 0.22

0.48 ± 0.12

Correctly identified MU counts

6.94 ± 9.28

1.00 ± 1.71

0.56 ± 1.03

50% MVC

Precision

0.83 ± 0.19

0.68 ± 0.27

0.59 ± 0.12

Sensitivity

0.65 ± 0.28

0.49 ± 0.36

0.37 ± 0.13

F1-score

0.68 ± 0.27

0.52 ± 0.35

0.43 ± 0.12

Correctly identified MU counts

2.31 ± 3.09

1.00 ± 1.32

0.19 ± 0.54