The search functionality is under construction.
The search functionality is under construction.

Statistical-Mechanical Analysis of Adaptive Volterra Filter for Nonwhite Input Signals

Koyo KUGIYAMA, Seiji MIYOSHI

  • Full Text Views

    0

  • Cite this

Summary :

The Volterra filter is one of the digital filters that can describe nonlinearity. In this paper, we analyze the dynamic behaviors of an adaptive signal processing system with the Volterra filter for nonwhite input signals by a statistical-mechanical method. Assuming the self-averaging property with an infinitely long tapped-delay line, we derive simultaneous differential equations that describe the behaviors of macroscopic variables in a deterministic and closed form. We analytically solve the derived equations to reveal the effect of the nonwhiteness of the input signal on the adaptation process. The results for the second-order Volterra filter show that the nonwhiteness decreases the mean-square error (MSE) in the early stages of the adaptation process and increases the MSE in the later stages.

Publication
IEICE TRANSACTIONS on Fundamentals Vol.E107-A No.1 pp.87-95
Publication Date
2024/01/01
Publicized
2023/07/13
Online ISSN
1745-1337
DOI
10.1587/transfun.2023KEP0009
Type of Manuscript
Special Section PAPER (Special Section on Circuits and Systems)
Category

Authors

Koyo KUGIYAMA
  Kansai University
Seiji MIYOSHI
  Kansai University

Keyword