Skip to main content

Table 7 Decomposition accuracy of ML-DRSNet, ML-DCNN, and MT-DCNN across 3 contraction intensities at their optimal window sizes and step sizes

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

140

140

Step size (data point)

50

50

10

Precision

0.93 ± 0.12

1.00 ± 0.00

0.96 ± 0.04

Sensitivity

0.84 ± 0.25

1.00 ± 0.00

0.92 ± 0.04

F1-score

0.85 ± 0.23

1.00 ± 0.00

0.92 ± 0.04

Correctly identified MU counts

10.90 ± 10.51

14.71 ± 8.23

11.90 ± 8.44