Table 1 Results of the projection...

Table 1

Results of the projection pursuit algorithm in terms of the correlation between the extracted signal $(y_{1})$ and source signals, values of the weight vector $(w_{1})$ ⁠, kurtosis of $y_{1}$ ⁠, and the angle between the optimal vector and the gradient vector $(α)$ during the iterations of the projection pursuit algorithm.

Results	iter = 1	iter =10	iter = 100	iter = 1000
0.3	0.33	0.99	1.00	$corr (y_{1}, s_{1})$
0.94	0.93	0.14	0.00	$corr (y_{1}, s_{2})$
0.14	0.13	0.01	0.01	$corr (y_{1}, s_{3})$
$w_{1}$	$(\begin{array}{l} - 0.50 \\ 0.23 \\ - 0.84 \end{array})$	$(\begin{array}{l} - 0.46 \\ 0.24 \\ - 0.85 \end{array})$	$(\begin{array}{l} 0.42 \\ 0.72 \\ - 0.5 \end{array})$	$(\begin{array}{l} 0.50 \\ 0.74 \\ - 0.45 \end{array})$
$K (y_{1})$	0.18	0.21	3.92	4.06
$α$	1.22	1.18	0.07	$5.3 e^{0 - 5}$

[ViewLarge]

Sharing Unavailable