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

Table 6

Comparison of proposed results against true values of INCAR model for 20 dB SNR.

μ	Method	Design parameters								MSE
		𝑝1	𝑝2	𝑎1	𝑎2	𝑎3	𝑞2𝑎1	𝑞2𝑎2	𝑞2𝑎3
(10^−04, 10^−08)	VLMS	1.349454	−0.744427	1.111856	0.406555	−0.186142	1.348684	1.163043	−0.409249	3.01𝐸−02
	KLMS	1.355797	−0.738500	0.777289	0.235371	0.385983	1.384078	0.601534	0.270259	1.22𝐸−01
	FLMS1	1.353185	−0.747387	0.997633	0.499185	−0.199222	1.681031	0.838613	−0.335203	3.43𝐸−06
	FLMS2	1.353038	−0.747304	0.997603	0.499176	−0.199241	1.680798	0.838613	−0.335052	3.37𝐸−06
(10^−03, 10^−05)	VLMS	1.344572	−0.743960	0.921542	0.588116	−0.222840	1.580521	0.967188	−0.370809	5.22𝐸−03
	KLMS	1.351239	−0.745972	0.971052	0.517420	−0.160944	1.518107	0.630421	0.060205	2.87𝐸−02
	FLMS1	1.355256	−0.749658	1.000849	0.497428	−0.198812	1.683680	0.847624	−0.336714	1.36𝐸−05
	FLMS2	1.355106	−0.749508	1.000717	0.497390	−0.198819	1.683638	0.847686	−0.336603	1.35𝐸−05
True values		1.350000	−0.750000	1.000000	0.500000	−0.200000	1.680000	0.840000	−0.336000