Adaptive Filters

S.B.Rabet
In the Name of GOD
Class Presentation For The Course :
Custom Implementation of DSP Systems
University of Tehran
2010
Pages 9 ~15 are copied from second reference [Overview of Adaptive Filters, Gner Arslan, from
Adaptive Filter Theory, 4e by Simon Haykin, 2002 Prentice Hall Inc]
All the materials are copy rights of their respective authors as listed in references.
2
introduction
Linear filters :
the filter output is a linear function of the filter input

Design methods:
1 The classical approach
frequency-selective filters such as
lowpass / bandpass / notch filters etc

2 Optimal filter design
Mostly based on minimizing the mean-square value
of the error signal

[1]
3
Wiener filter
work of Wiener in 1942 and Kolmogorov in 1939

it is based on a priori
statistical information

when such a priori
information is not available,
which is usually the case,
it is not possible to design
a Wiener filter in the first
place





[1]
4
Adaptive filter
the signal and/or noise characteristics are often
nonstationary and the statistical parameters vary
with time


An adaptive filter has an adaptation algorithm, that is
meant to monitor the environment and vary the filter
transfer function accordingly


based in the actual signals received, attempts to find
the optimum filter design




[1]
5
Adaptive filter
In a stationary environment, the filter is expected to
converge, to the Wiener filter

In a nonstationary environment,
the filter is expected to
track time variations and
vary its filter coefficients
accordingly




[1]
6
Adaptive filter
The basic operation now involves two
processes :

1. a filtering process, which produces an output signal
in response to a given input signal.

2. an adaptation process, which aims to adjust the
filter parameters (filter transfer function) to the
(possibly time-varying) environment
Often, the (avarage) square value of the error signal
is used as the optimization criterion


[1]
7
Adaptive filter
Because of complexity of the optimizing algorithms
most adaptive filters are digital filters that perform
digital signal processing

When processing
analog signals,
the adaptive filter
is then preceded
by A/D and D/A
convertors.

[1]
8
Adaptive filter

The generalization to adaptive IIR filters leads to
stability problems

Its common to use
a FIR digital filter
with adjustable
coefficients.
[1]
9
LMS Algorithm
Most popular adaptation algorithm is LMS
Define cost function as mean-squared error

Based on the method of steepest descent
Move towards the minimum on the error surface to
get to minimum
gradient of the error surface estimated at every
iteration


|
|
.
|

\
|
|
|
|
.
|

\
|

|
|
|
.
|

\
|
+
|
|
|
.
|

\
|
=
|
|
|
.
|

\
|
signal
error
vector
input
tap
parameter
rate
- learning
vector
weight - tap of
value old
vector
weigth - tap of
value update
[2]
10
LMS Algorithm
[2]
) ( ) ( 2 ) ( ) 1 ( ) ( ) ( 2 ) (
) ( ) ( 2
) (
) ( ) (
) (
) ( 2
) (
) ( 2
) (
), ( ) ( ) 1 (
) (

) ( ) ( ) (
)] ( ),..., 1 ( ), ( [ ) ( ], ,..., , [ ) (
2
2
1
0
) ( ) ( ) (
2
2
2
1 0
n X n e n W n W n X n e n e
i n x n e
W
n e
i n x n W y
W
n y
n e
W
n e
n e
W
n e
StepSize n e n W n W
n e
n y n d n e
N n x n x n x n X w w w n W
i
N
i
i
n y n d n e
i i
N

+ = + = V
=
c
c
=
c
c
=
c
c
=
c
c
= V = +
=
=
= =

=
=
11
Stability of LMS
The LMS algorithm is convergent in the mean square
if and only if the step-size parameter satisfy

Here
max
is the largest eigenvalue of the correlation
matrix of the input data
More practical test for stability is

Larger values for step size
Increases adaptation rate (faster adaptation)
Increases residual mean-squared error
max
2
0

< <
power signal input
2
0 < <
[2]
12
Applications of Adaptive Filters:
Identification
Used to provide a linear model of an unknown plant






Applications:
System identification
[2]
13
Applications of Adaptive Filters:
Inverse Modeling
Used to provide an inverse model of an unknown
plant






Applications:
Equalization (communications channels)
[2]
14
Applications of Adaptive Filters:
Prediction
Used to provide a prediction of the present value of a
random signal





Applications:
Linear predictive coding
[2]
15
Applications of Adaptive Filters:
Interference Cancellation
Used to cancel unknown interference from a primary
signal




Applications:
Echo / Noise cancellation
hands-free carphone, aircraft headphones etc
[2]
Example:
Acoustic Echo Cancellation
16
[1]
A new work
Novel Adaptive IIR Filter for Frequency
Estimation and Tracking

In many applications we may want to estimate (track)
the signals fundamental frequency as well as any
harmonic frequencies

In this article, we present a novel adaptive harmonic IIR
notch filter with a single adaptive coefficient to
efficiently perform frequency estimation and tracking
in a harmonic frequency environment
17
[3]
Structure
frequency estimation of a measured signal x(n)



V(n) is a white Gaussian noise

To estimate frequency in such a harmonic frequency
environment, a IIR notch filter presented for the
case of M=3 (the fundamental and
two harmonics)
18
[3]
Pole zero plot
19








Parameter r is chosen to be close to, but less than,
one to achieve narrowband notches and avoid any
filter stability problems
[3]
Transfer function







the transfer function has only one adaptive coefficient

Our objective, then, is to minimize the power of the
last subfilter output

20
[3]
MSE









we could determine a frequency capture range based
on the plotted MSE function
21
[3]
Performance
22
[3]
References
[1] INTRODUCTIONto ADAPTIVE SIGNAL PROCESSING Marc
Moonen ,Department of Electrical Engineering ESAT/SISTA
K.U. Leuven, Leuven, Belgium
[2] Overview of Adaptive Filters, Gner Arslan, from Adaptive
Filter Theory, 4e by Simon Haykin, 2002 Prentice Hall Inc
[3] Li Tan , Jean Jiang Novel Adaptive IIR Filter for Frequency
Estimation and Tracking , IEEE SIGNAL PROCESSING MAGAZINE
[186] NOVEMBER 2009
23