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

Table 13

Selection of optimal learning rule for various NN models on test dataset.

S.N.	NN	Signal	Learning rule
			Momentum	Conjugate gradient	Levenberg Marquardt	Quick propagation	Step	Delta- bar- delta
1	MLP	Noise	0.7786	0.76672	0.77414	0.77388	0.77365	0.76857
		EMG	0.5840	0.57205	0.57182	0.56866	0.57026	0.57125
2	FTLRNN	Noise	0.99843	0.99617	0.99781	0.99806	0.99842	0.99792
		EMG	0.99731	0.99572	0.99684	0.99756	0.99695	0.99787
3	RBF	Noise	0.77314	0.7737	0.77382	0.77335	0.77335	0.7724
		EMG	0.57059	0.5712	0.57186	0.5718	0.57184	0.5711