Xiaowen Zhang

Publication Date

1999

Document Type

Dissertation/Thesis

First Advisor

Woo, Peng-Yung

Degree Name

M.S. (Master of Science)

Legacy Department

Department of Electrical Engineering

LCSH

Neural networks (Computer science); Nonlinear systems; Echo suppression (Telecommunication)

Abstract

In this thesis, the introduction of artificial neural network is proposed and its application advantages are analyzed in Chapter 1. In Chapter 2, the research begun in the most important and most widely used neural network algorithm for logical operations: AND, OR, and XOR using a three-layer neural network structure is discussed. Different levels of noise to the algorithm performance are compared and analyzed from a theoretical and a simulation point of view. In Chapter 3, nonlinear system identifications are discussed and three different system models are used to verify the effectiveness of algorithm and structure. The three different acoustic echo cancellation structures are proposed and a neural network is used to mimic the nonlinear characteristics of a loudspeaker. Computer simulation results are available at the end of each section to show the powerful ability of a neural network in various applications and research areas.

Comments

Includes bibliographical references (pages [80]-87)

Extent

ix, 103 pages

Language

eng

Publisher

Northern Illinois University

Rights Statement

In Copyright

Rights Statement 2

NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.

Media Type

Text

Download

Share

COinS