Skip to main content

Table 9 Decomposition accuracy of ML-DRSNet, ML-DCNN, and MT-DCNN across 3 contraction intensities at a window size of 20 data points and a step size of 10 data points

From: A multi-label deep residual shrinkage network for high-density surface electromyography decomposition in real-time

Method

ML-DRSNet

ML-DCNN

MT-DCNN

Window size (data point)

20

20

20

Step size (data point)

10

10

10

Precision

0.86 ± 0.18

0.71 ± 0.24

0.66 ± 0.15

Sensitivity

0.73 ± 0.29

0.49 ± 0.32

0.45 ± 0.16

F1-score

0.76 ± 0.28

0.53 ± 0.31

0.51 ± 0.16

Correctly identified MU counts

8.27 ± 9.23

2.54 ± 3.96

0.92 ± 1.56