Document Type
Thesis
Date of Award
10-31-1993
Degree Name
Master of Science in Electrical Engineering - (M.S.)
Department
Electrical Engineering
First Advisor
Nirwan Ansari
Second Advisor
Zoran Siveski
Third Advisor
Edwin Hou
Abstract
Recently, a new class of adaptive filters called Generalized Adaptive Neural Filters (GANFs) has emerged. They share many characteristics in common with stack filters, include all stack filters as a subset. The GANFs allow a very efficient hardware implementation once they are trained. However, there are some problems associated with GANFs. Three of these arc slow training speeds and the difficulty in choosing a filter structure and neural operator.
This thesis begins with a tutorial on filtering and traces the GANF development up through its origin -- the stack filter. After the GANF is covered in reasonable depth, its use as an image processing filter is examined. Its usefulness is determined based on simulation comparisons with other common filters. Also, some problems of GANFs are looked into. A brief study which investigates different types of neural networks and their applicability to GANFs is presented. Finally, some ideas on increasing the speed of the GANF are discussed. While these improvements do not completely solve the GANF's problems, they make a measurable difference and bring the filter closer to reality.
Recommended Citation
Hanek, Henry Steven, "Simplification of the generalized adaptive neural filter and comparative studies with other nonlinear filters" (1993). Theses. 1777.
https://digitalcommons.njit.edu/theses/1777
