Soner Bekleric Title of Thesis: Nonlinear Prediction via Volterra Ser
Soner Bekleric Title of Thesis: Nonlinear Prediction via Volterra Ser
Soner Bekleric Title of Thesis: Nonlinear Prediction via Volterra Ser
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
4.5. SYNTHETIC AND REAL DATA EXAMPLES 65<br />
Time (s)<br />
0<br />
0.2<br />
0.4<br />
0.6<br />
Traces<br />
10 20<br />
(a)<br />
Time (s)<br />
Time (s)<br />
0<br />
0.2<br />
0.4<br />
0.6<br />
0<br />
0.2<br />
0.4<br />
0.6<br />
Traces<br />
10 20<br />
(b)<br />
Traces<br />
10 20<br />
Time (s)<br />
Time (s)<br />
0<br />
0.2<br />
0.4<br />
0.6<br />
Traces<br />
10 20<br />
(c)<br />
0.6<br />
(e) (d) (e) (f)<br />
0<br />
0.2<br />
0.4<br />
Traces<br />
10 20<br />
Figure 4.12: 2-D synthetic data for comparison <strong>of</strong> prediction between linear prediction<br />
theory and third order <strong>Volterra</strong> series. (a) Original data. (b) <strong>Prediction</strong><br />
using the third-order <strong>Volterra</strong> series with parameters p = 3, q = 3, and r = 3. (c)<br />
Error between original data and predicted <strong>via</strong> the third-order <strong>Volterra</strong> series. (d)<br />
<strong>Prediction</strong> using linear prediction theory with parameter p = 3. (e) Error between<br />
original data and predicted data <strong>via</strong> linear prediction theory.<br />
In Figure 4.16 I portray the predictions associated with linear, quadratic, and cubic<br />
terms.<br />
Figures 4.15(b) and 4.15(d) show data prediction using a third-order <strong>Volterra</strong><br />
series with parameters p = 6, q = 6, and r = 6 and using linear prediction theory