Intelligent Noise Removal from EMG Signal Using Focused Time-Lagged Recurrent Neural Network

Table 16

Comparison of all the NN architectures on test dataset.

NN model	Transfer function	Learning rule	Mean square error MSE	Correlation coefficient r	Epochs	Time elapsed/ epoch/exemplar in microseconds	% error
MLP (1-15-10-2)	Tanh	Momentum	0.02501 (noise) 0.02482(EMG)	0.78114 (noise) 0.58433 (EMG)	1000	19.16	253
FTLRNN (1-27-2)	Linear	Momentum	0.000067 (noise) 0.000048 (EMG)	0.99950 (noise) 0.99939 (EMG)	1000	14	10
RBF (CC-05)	Linear	LM	0.02470 (noise) 0.02482 (EMG)	0.78414 (noise) 0.58509 (EMG)	1000	8.3	293