Identification of Input Nonlinear Control Autoregressive Systems Using Fractional Signal Processing Approach

Table 8

Comparison of proposed results against true values of INCAR model for 3 dB SNR.

μ	Method	Design parameters								MSE
		𝑝1	𝑝2	𝑎1	𝑎2	𝑎3	𝑞2𝑎1	𝑞2𝑎2	𝑞2𝑎3
(10^−04, 10^−08)	VLMS	1.350033	−0.747776	1.151411	0.382217	−0.174445	1.266046	1.237098	−0.428614	4.69𝐸−02
	KLMS	1.356493	−0.736365	0.748964	0.105174	0.542420	1.362022	0.609956	0.290923	1.65𝐸−01
	FLMS1	1.352386	−0.750941	0.992991	0.491026	−0.198780	1.686456	0.849316	−0.338108	3.38𝐸−05
	FLMS2	1.352534	−0.750836	0.993316	0.490747	−0.198439	1.686445	0.849539	−0.337726	3.44𝐸−05
(10^−03, 10^−05)	VLMS	1.349324	−0.747288	0.983402	0.533690	−0.203984	1.423701	1.105389	−0.402156	1.77𝐸−02
	KLMS	1.350614	−0.760252	1.136970	0.030726	0.119125	1.612852	0.232501	0.372932	1.52𝐸−01
	FLMS1	1.351001	−0.731407	0.993154	0.493843	−0.214263	1.694738	0.819746	−0.318643	1.95𝐸−04
	FLMS2	1.351107	−0.731604	0.995350	0.492513	−0.216675	1.693931	0.819381	−0.318775	2.01𝐸−04
True values		1.350000	−0.750000	1.000000	0.500000	−0.200000	1.680000	0.840000	−0.336000