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

Table 7

Comparison of proposed results against true values of INCAR model for 10 dB SNR.

μ	Method	Design parameters								MSE
		𝑝1	𝑝2	𝑎1	𝑎2	𝑎3	𝑞2𝑎1	𝑞2𝑎2	𝑞2𝑎3
(10^−04, 10^−08)	VLMS	1.351468	−0.744938	1.047010	0.486303	−0.200102	1.285267	1.225023	−0.427779	3.94𝐸−02
	KLMS	1.356262	−0.736962	0.956832	0.185102	0.259909	1.220949	0.529005	0.495796	1.64𝐸−01
	FLMS1	1.356850	−0.745266	1.001581	0.494077	−0.202190	1.670903	0.837135	−0.334630	2.56𝐸−05
	FLMS2	1.356608	−0.745109	1.001695	0.493895	−0.202230	1.671239	0.837177	−0.334908	2.48𝐸−05
(10^−03, 10^−05)	VLMS	1.349757	−0.747542	0.945167	0.564599	−0.216172	1.511909	1.011739	−0.377157	8.36𝐸−03
	KLMS	1.355306	−0.750178	1.058421	0.333366	−0.033855	1.341960	0.926972	−0.080043	3.08𝐸−02
	FLMS1	1.350819	−0.748919	0.998394	0.491951	−0.179965	1.688782	0.847405	−0.340293	7.76𝐸−05
	FLMS2	1.350853	−0.748833	0.997694	0.492029	−0.179449	1.688987	0.847312	−0.340771	8.13𝐸−05
True values		1.350000	−0.750000	1.000000	0.500000	−0.200000	1.680000	0.840000	−0.336000