Chapter 6 and 7

Adaptive signal processing and its application

Applications of Digital signal processing

What Is Adaptive signal processing

Adaptive signal processing concerns with processing of

signals where the processing parameters are adjusted
continuously to suit time varying signal environmental
conditions.
The study of adaptive signal processing involves
development of various adaptation algorithms and
assessing them in terms of convergence rate, computational
complexity, robustness against noisy data, hardware
complexity, numerical stability etc.

1 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

As previously discussed, the design of digital filters with

fixed coefficients requires well-defined prescribed
specifications.
However, there are situations where the specifications are
not available, or are time varying. The solution in these
cases is to employ adigital filter with adaptive coefficients,
known as adaptive filters.
Since no specifications are available, the adaptive algorithm
that determines the updating of the filter coefficients
requires extra information that is usually given in the form
of a signal. This signal is in general called a desired or
reference signal,whose choice is normally a tricky task that
depends on the application.

2 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

Adaptive filters are considered nonlinear systems, therefore

their behavior analysis is more complicated than for fixed
filters. On the other hand, because the adaptive filters are
self-designing filters, from the practitioner’s point of view
their design can be considered less involved than in the
case of digital filters with fixed coefficients.
The general setup of an adaptive-filtering environment is
illustrated in Fig 1, where k is the iteration number, x(k)
denotes the input signal, y(k) is the adaptive filter output
signal, and d(k) defines the desired signal. The error signal
e(k) is calculated as d(k)-y(k)
The error signal is then used to form a performance or
objective function that is required by the adaptation
algorithm in order to determine the appropriate updating
of the filter coefficients. The minimization of the objective
function implies that the adaptive-filter output signal is
matching the desired signal in some sense.
3 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

Figure 1: General Adaptive-Filter Configuration

4 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

The complete specification of an adaptive system, as shown in

Fig 1, consists of three items.
1 Application: The type of application is defined by the
choice of the signals acquired from the environment to be
the input and desired-output signals. Some application
of adaptive filtering are echo cancellation, equalization
of channels, system identification, signal enhancement,
adaptive beam-forming and noise canceling.
2 Adaptive-filter structure: The adaptive filter can be
implemented in a number of different structures or
realizations. The choice of the structure can influence the
computational complexity (amount of arithmetic operations
per iteration) of the process and also the necessary number
of iterations to achieve a desired performance level.

5 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

Basically, there are two major classes of adaptive digital

filter realizations, distinguished by the form of the impulse
response, namely the finite duration impulse response
(FIR) filter and the infinite-duration impulse response
(IIR) filters. FIR filters are usually implemented with non
recursive structures,whereas IIR filters utilize recursive
realization.
Adaptive FIR filter realizations: The most widely used
adaptive FIR filter structure is the transversal filter, also
called tapped delay line, that implements an all-zero
transfer function with a canonic direct-form realization
without feedback. For this realization, the output signal
y(k) is a linear combination of the filter coefficients, that
yields a quadratic mean-square error (MSE = E[ke(k)k2 ]
function with a unique optimal solution. Other alternative
adaptive FIR realizations are also used in order to obtain
improvements as compared to the transversal filter
structure, in terms of computational complexity, speed of 6 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

Adaptive IIR filter realizations: The most widely used

realization of adaptive IIR filters is the canonic direct-form
realization, due to its simple implementation. However,
there are some inherent problems related to recursive
adaptive filters which are structure dependent, such as
pole-stability monitoring requirement and slow speed of
convergence.
To address these problems, different realizations were
proposed attempting to overcome the limitations of the
direct-form structure. Among these alternative structures,
the cascade, the lattice, and the parallel realizations are
considered because of their unique features as will be
discussed in the previous Chap.

7 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

1 Algorithm: The algorithm is the procedure used to adjust

the adaptive filter coefficients in order to minimize a
prescribed criterion. The algorithm is determined by
defining the search method (or minimization algorithm),
the objective function, and the error signal nature. The
choice of the algorithm determines several crucial aspects
of the overall adaptive process, such as existence of
suboptimal solutions, biased optimal solution, and
computational complexity.

8 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

The Least Mean-Square(LMS) Algorithm

In many practical applications, the statistics of d(n) and x(n)
are unknown. Therefore, the method of steepest descent cannot
be used directly since it assumes exact knowledge of the
gradient vector. The LMS algorithm uses the instantaneous
squared error, e2 (n), to estimate the MSE. That is
ζ(n) = e2 (n)
The concept of steepest descent can be implemented in the
following algorithm:
µ
w(n + 1) = w(n) −
ζ(n) (1)
2
Therefore, the gradient estimate used by the LMS algorithm
can be written as
∇ζ(n) = 2[∇e(n)]e(n)
Since e(n) = d(n) − wT (n)x(n), e(n) = −x(n), the gradient
estimate becomes
∇ζ(n) = −2x(n)e(n) 9 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

Substituting this gradient estimate into the steepest-descent

algorithm of Equation (1), we have.
w(n + 1) = w(n) + µx(n)e(n)
This is the well-known LMS algorithm, or stochastic gradient
algorithm. This algorithm is simple and does not require
squaring, averaging, or differentiating.
The LMS algorithm is illustrated in Figure 2

Figure 2: Block diagram of an adaptive filter with the LMS algorithm

10 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

LMS algorithm can be summarized as follows:

1 Determine L, µ, and w(0), where L is the length of the
filter, µ is the step size, and w(0) is the initial weight
vector at time n = 0.
2 Compute the adaptive filter output.
PL−1
y(n)= I=0 w1 (n)x(n − I)
3 Compute the error signal
e(n) = d(n) − y(n)
4 Update the adaptive weight vector using the LMS
algorithm:
w1 (n + 1) = w1 (n) + µx(n − I)e(n)

11 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

Reading assignment (RLS and Kalman filters)

Algorithm!!!

12 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

Applications of Digital signal processing

Digital signal processing is used in several areas, including the
following
1) Telecommunications: Wireless or mobile phones are rapidly
replacing wired (landline) telephones, both of which are
connected to a large-scale telecommunications network.
They are used for voice communication as well as data
communications. So also are the computers connected to a
different network that is used for data and information
processing.
Computers are used to generate, transmit, and receive an
enormous amount of information through the Internet and
will be used more extensively over the same network, in the
coming years for voice communications also.
This technology is known as voice over Internet protocol
(VoIP) or Internet telephony.
13 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

2) Speech Processing:
The quality of speech transmission in real time over
telecommunications networks from wired (landline)
telephones or wireless (cellular) telephones is very high.
Speech recognition, speech synthesis, speaker verification,
speech enhancement, text-to-speech translation, and
speech-to-text dictation are some of the other applications
of speech processing.
3) Consumer Electronics:
4) Biomedical Systems: The variety of machines used in
hospitals and biomedical applications is staggering.
Included are X-ray machines, MRI, PET scanning,bone
scanning, CT scanning, ultrasound imaging, fetal
monitoring, patient monitoring, and ECG and EEC
mapping. Another example of advanced digital signal
processing is found in hearing aids and cardiac pacemakers.
14 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

5) Image Processing:
Image enhancement, image restoration, image
understanding, computer vision, radar and sonar
processing, geophysical and seismic data processing, remote
sensing, and weather monitoring are some of the
applications of image processing.
Reconstruction of two-dimensional (2D) images from
several pictures taken at different angles and
three-dimensional (3D) images from several contiguous
slices has been used in many applications.
6) Military Electronics:
The applications of digital signal processing in military and
defense electronics systems use very advanced techniques.
Some of the applications are GPS and navigation, radar
and sonar image processing, detection and tracking of
targets, missile guidance, secure communications, jamming
and countermeasures, remote control of surveillance
aircraft, and electronic warfare 15 / 16
 Chapter 6 and 7
Adaptive signal processing and its application
Applications of Digital signal processing

7) Aerospace and Automotive Electronics:

Applications include control of aircraft and automotive engines,
monitoring and control of flying performance of aircraft,
navigation and communications, vibration analysis and antiskid
control of cars, control of brakes in aircrafts, control of
suspension, and riding comfort of cars.
8) Industrial Applications: Numerical control, robotics, control
of engines and motors, manufacturing automation, security
access, and videoconferencing are a few of the industrial
applications.

16 / 16