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
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
Contents<br />
1 Introduction 1<br />
1.1 Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3<br />
1.2 Motivation and Goals <strong>of</strong> the <strong>Thesis</strong> . . . . . . . . . . . . . . . . . . 5<br />
1.3 <strong>Thesis</strong> Outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5<br />
2 Linear Systems and <strong>Prediction</strong> 7<br />
2.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7<br />
2.2 Linear Process . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8<br />
2.3 Linear <strong>Prediction</strong> . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10<br />
2.3.1 Forward and backward prediction . . . . . . . . . . . . . . . 12<br />
2.3.2 Estimating AR coefficients <strong>via</strong> Yule-Walker Equations . . . . 12<br />
2.3.3 Estimating AR coefficients <strong>via</strong> Burg’s algorithm . . . . . . . 14<br />
2.3.4 Computing the AR coefficients without limiting the aperture 16<br />
2.4 1-D Synthetic and Real Data Examples . . . . . . . . . . . . . . . . 19<br />
2.5 Power Spectrum . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23<br />
2.6 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24<br />
3 <strong>Nonlinear</strong> <strong>Prediction</strong> 26<br />
3.1 <strong>Nonlinear</strong> Processes <strong>via</strong> the <strong>Volterra</strong> <strong>Ser</strong>ies . . . . . . . . . . . . . . 26<br />
3.1.1 Time domain representation . . . . . . . . . . . . . . . . . . 27<br />
3.1.2 Frequency domain representation <strong>of</strong> <strong>Volterra</strong> kernels . . . . . 28<br />
3.1.3 Symmetry property <strong>of</strong> <strong>Volterra</strong> kernels . . . . . . . . . . . . 30<br />
3.2 <strong>Nonlinear</strong> Modeling <strong>of</strong> Time <strong>Ser</strong>ies . . . . . . . . . . . . . . . . . . 32<br />
3.3 1-D Synthetic and Real Data Examples . . . . . . . . . . . . . . . . 40<br />
2