Adaptive Filtering

(3-0-0-3)

CMPE Degree: This course is Not Applicable for the CMPE degree.

EE Degree: This course is Not Applicable for the EE degree.

Lab Hours: 0 supervised lab hours and 0 unsupervised lab hours.

Technical Interest Group(s) / Course Type(s): Digital Signal Processing

Course Coordinator:

Prerequisites: ECE 4270

Catalog Description

Basic theory of adaptive filter design and implementation.
Steepest descent, LMS algorithm, nonlinear adaptive filters, and
neural networks. Analysis of performance and applications.

Course Outcomes

Not Applicable

Strategic Performance Indicators (SPIs)

Not Applicable

Topical Outline

Background (1 week)
Eigenanalysis
Review of Discrete-time random processes
FIR Wiener filters (1 week)
Derivation of the Wiener-Hopf equations
Principle of orthogonality
Problems and applications
Solving the Wiener-Hopf equations.
The Discrete Kalman Filter (1 week)
Gradient-based adaptive filters (4 weeks)
Steepest descent
The LMS algorithm
Performance Analysis
Variations on the LMS algorithm
Examples and comparison of techniques
Applications
Gradient Adaptive Lattice Filter (0.5 weeks)
Recursive least squares (1.5 weeks)
Transversal filters
Lattice filters - optional
Performace of the RLS algorithm
Tracking of time-varying systems (0.5 weeks) - Chapter 16 of Haykin
Adaptive IIR filters (1.5 weeks)
IIR LMS
Fientuch and Horvath algorithms
HARF and SHARF
Examples and applications
Nonlinear adaptive filters (3 weeks) - Chapters 18-20 of Haykin
Order statistic adaptive filters and Volterra systems
Blind deconvolution - decision directed feedback
Back propagation learning
Radial basis function networks
Examples
Other Applications - optional
Adaptive line enhancement
Adaptive spectrum estimation, frequency tracking
Adaptive signal modeling