Design of Adaptive Filter Using Jordan/Elman Neural Network in a Typical EMG Signal Noise Removal

Table 5

Serial no.	Type of ANN	Hidden layer variation H1 H2 H3	Correlation coefficient (𝑟)	MSE			𝑁/𝑃	𝑡 (𝜇s)
				Training	Cross validation	Testing
01	MLP	08,04,02	0.726 960 433	0.011 620 758	0.019 586 198	0.014 066 105	9.7826	6.1
02	Gen FF	08,04,02	0.738 815 896	0.011 513 017	0.018 595 822	0.01 154 671	9.7826	185.1
03	Mod NN	08,04,02	0.734 250 027	0.012 326 123	0.023 655 146	0.016 096 204	9.7826	37.9
04	RBF	08,04,02	0.710 938 982	0.011 711 991	0.020 447 456	0.014 686 126	9.7826	42.1
05	Time-lag Rec	08,04,02	0.703 300 064	0.009 955 203	0.023 340 290	0.016 268 503	9.7826	1.667
06	Recurrent NN	08,04,02	0.739 407 946	0.009 971 926	0.018 246 162	0.013 818 155	9.7826	493.8