Skip to main content

Table 2 Performance comparison of non-linear models and optimal number of hidden units (HU)

From: Combining two open source tools for neural computation (BioPatRec and Netlab) improves movement classification for prosthetic control

BioPatRec MLP 32 HU 2 × 32 HU 64 /74 HU
Outp. type Acc SD Acc SD Acc SD
Single 0.941 0.062 0.951 0.054 0.923a 0.055
Multiple 0.954 0.047 0.949 0.049 0.953b 0.043
Netlab MLP 32 HU 64 /74 HU
Outp. type Acc SD Acc SD
Single 0.983 0.024 0.987 a 0.019
Multiple 0.970 0.033 0.980 b 0.025
  1. Italics highest accuracy is significant against all other accuracies for single/multiple output type with p < 0.01
  2. a 64 HU
  3. b 74 HU