FIR Filter Design Using Mixed Algorithm: Vikash Kumar, Mr. Vaibhav Purwar
FIR Filter Design Using Mixed Algorithm: Vikash Kumar, Mr. Vaibhav Purwar
11 www.erpublication.org
FIR Filter Design Using Mixed Algorithm
(3) Optimal filter design methods is usually described as a string of symbols from (0,1). These
components of the chromosomes are then labeled as genes.
A. Kaiser window
Kaiser window is a well known flexible window and widely B. Crossover
used for FIR filter design and spectrum analysis, since it The crossover operator is the most important operator of GA.
achieves close approximation to the discrete pro late In crossover, generally two chromosomes, called parents, are
spheroidal functions that have maximum energy combined together to form new chromosomes, called
concentration in the main lobe. With adjusting its two offspring. The parents are selected among existing
independent parameters, namely the window length and the chromosomes in the population with preference towards
shape parameter, it can control the spectral parameters main fitness so that offspring is expected to inherit good. By one
lobe width and ripple ratio for various applications. Side lobe from two parent point crossover method, for a chromosome of
roll-off ratio is another spectral parameter and important for length, l, a random number c between 1 and l is first
some applications. For beam forming applications, the higher generated. The first child chromosome is formed by
side lobe roll-off ratio means, that it can reject far end appending the last l-c elements of the first parent chromosome
interferences better. For filter design applications, it can to the first c elements of the second parent chromosome. The
reduce the far end attenuation for stop band energy. And for second child chromosome is formed by appending the last l-c
speech processing, it reduces the energy leak from one band elements of the second parent chromosome to the first c
to another. elements of the first parent chromosome. Probability of
B. Optimal Filter Design Methods crossover ranges from 0.6 to6 to0.95
Optimization is the act of obtaining the best results under C. Mutation
given circumstances. Optimization can be defined as the Mutation is another important operator in CGA, though it is
process of finding the condition that gives the maximum or usually considered as a background operator. It operates
minimum value of the function. If x* corresponds the independently on each individual by probabilistic perturbing
minimum value of function f(x), the same point also each bit string. The mutation operator introduces random
corresponds to maximum value of the function f(x). Thus changes in to characteristic of chromosomes. Mutation is
optimization can be taken to mean minimization since the generally applied at the gene level. There is a chance that a
maximum of the function can be found by seeking of the gene of a child is changed randomly. Generally the chances of
negative of the same number. mutation are low. Therefore, the new chromosome produced
by mutation will not be very different from the original one.
IV. GENETIC ALGORITHM Mutation is a unary operator that is usually applied with a low
A Genetic algorithm (GA) is an optimization technique that is probability An usual way to mutate used in CGA is to generate
based on the evolution theory. Instead of searching for a a random number v between 1 and l and then make a random
solution to a problem in the state space (like the traditional change in the vth element of the string with probability
search algorithms do), a GA works in the solution space and pm(0, 1) Typically, the probability for bit mutation changes
builds new, hopefully better solution based on existing ones. from 0.001 to 0.01
GA operates with a collection of chromosomes, called a
population. The population is normally randomly initialized.
The population includes
fitter and fitter solution, and eventually it converges, meaning
that it is dominated by a single solution. The general idea
behind GA is that it builds a better solution by somehow
combining the good parts of other solutions (schemata
Figure 1: One-point Crossover and Mutation operators
theory), just like nature does by combining the DNA of living
beings [10]. In GA, different operators are to generate new
solutions from existing ones. These operators are based on D. Genetic Algorithm Procedure
reproductions, Reproduction operators are crossover and
mutation. The size of each chromosome must remain the same The genetic algorithm loops over an iteration process to make
for crossover to be applied. Fittest chromosomes are selected the population evolve [12]. It consist the following steps:
in each generation to produce offspring which replace the 1. The first step consists in selecting individuals for
previous generation. The good individuals remain in the reproduction. This selection is done randomly with a
population and reproduce; while the bad individuals are probability depending on the relative fitness of the individuals
eliminated from the population. Finally the population will so that best ones are often chosen for reproduction than poor
consist only of the best individuals fulfilling the design ones.
specifications. The genetic algorithm is an artificial genetic 2. Reproduction: In the second step, offspring are bred by
system based on the process of natural selection and genetic the selected individuals. For generating new chromosomes,
operators. Genetic algorithm is a heuristic algorithm which the algorithm can use both recombination and mutation.
tries to find the optimal results by decreasing the value of the 3. Evaluation: Then the fitness of the new chromosomes is
objective function. evaluated.
A. Initialization 4. Replacement: During the last step, individuals from the
old population are killed and replaced by the new ones. The
In the initialization, the first thing to do is to decide the coding
algorithm is stopped when the population converges towards
structure. Coding for a solution, termed a chromosome in GA,
the optimal solution.
12 www.erpublication.org
International Journal of Engineering and Technical Research (IJETR)
ISSN: 2321-0869 (O) 2454-4698 (P) Volume-7, Issue-7, July 2017
To design a linear phase FIR filter, we must minimize the
error between actual and ideal output. There exist some forms
of error function for the filter design. One of them is the
least-squares method. We define the error function as the
error between the desired magnitude and the actual amplitude
at a certain frequency, that is
F. Coefficient Encoding
The filter impulse response coefficients, h (0) to h (N), are
Figure 2 Flow Chart of GA sufficient to represent a digital FIR filter. Thus, N+1
coefficients of the filter form the genome and the particle
position in the GA and the PSO, respectively. Each
E. Application of Genetic Algorithm to FIR Filter Design coefficient is represented by a floating number in the range
A digital FIR filter is characterized by the following transfer [-1, 1], inclusive. G. Fitness Function A fitness function is a
function, particular type of objective function that is used to
summarize, as a single figure of merit. Fitness function must
be devised for each problem to be solved. Given a particular
chromosome, the fitness function returns a single numerical
fitness, figure of merit, which is supposed to be
In the above expression, N is the order of the filter and h(n)
proportional to the utility or ability of the individual
represent the filter coefficients to be determined in the design
which that chromosome represents. We use the total squared
process. Designing the FIR filters as minimum phase provides
error as the fitness function of FIR digital filter, that is:
some important advantages. Minimum phase filters have two
main advantages: Reduced filter length and Minimum group
delay. Minimum phase filters can simultaneously meet delay
and magnitude response constraints yet generally require
fewer computations and less memory than linear phase. V. ARTIFICIAL NEURAL NETWORKS
Recently, GA has been emerged into optimum filter designs. An Artificial Neural Network (ANN) also known as Neural
The characteristics of multi-objective, coded variables and Network (NN) is a computational model based on the
natural selection make GA different from other optimization structure and function of biological neural network [1]. In
techniques. Filters designed by GA have the potential of other words ANN is computing system which is made up of a
obtaining near global optimum solution [13]. FIR digital filter number of simple processing elements (the computer
has a finite number of nonzero entries of its impulse response equivalent of neurons, Nodes) that are highly interconnected
such as h[n], n=0,1,,N. Generally assume implicitly that to each other through synaptic weights. The number of nodes,
h[n] 0 , h[0] 0. The transfer function of the FIR filter is their organization and synaptic weights of these connections
given in eq. (2) and the frequency response of form is: determine the output of the network. ANN is an adaptive
system that changes its structure/weights based on given set of
inputs and target outputs during the training phase an
produces final outputs accordingly. ANN is particularly
Consider the ideal frequency response Hd(ej) with the
effective for predicting events when the network have a large
samples divided into equal frequency interval, Thus we can
database of prior examples to draw. The common
get,
implementation of ANN has multiple inputs, weight
associated with each input, a threshold that determine if the
neuron should fire, an activation function that determine the
where, Hd(k) is regarded as the frequency response of the output and mode of operation. The general structure of a
filter to design. Equation (4) can be rewritten as neural network has three types of layers that are
interconnected: input layer, one or more hidden layers and
output layer as shown in Figure 3.
13 www.erpublication.org
FIR Filter Design Using Mixed Algorithm
Here, there is a flat pass band below pass band frequency (P)
=2500 Hz and flat attenuation band above stop band
frequency (s) =3000 Hz. Here we have applied Genetic
Algorithm with two parents and three parents separately on
filter response which is obtained by using Kaiser Window.
Then the results are studied and compared .When we are
using only two parents, we get the magnitude response versus
frequency curve as shown in Fig.7, Fig.9. But, when we are
using three parents, we get a better magnitude response versus
Figure 4: Feed forward back propagation neural network
frequency curve as shown in Fig.8, Fig.10.
14 www.erpublication.org
International Journal of Engineering and Technical Research (IJETR)
ISSN: 2321-0869 (O) 2454-4698 (P) Volume-7, Issue-7, July 2017
outputs obtained it is clear that GA offers a quick, simple and
automatic method of designing low pass FIR filters that are
very close to optimum in terms of magnitude response,
frequency response and in terms of phase variation. From the
outputs obtained it is clear that more better results in ANN
offers a quick, simple and automatic method of designing low
pass FIR filters that are very close and ripple free to optimum
in terms of magnitude response, frequency response and in
terms of phase variation.
A technique of using three parents using Kaiser Window, GA
and ANN has been proposed and outputs are compared with
the outputs obtained using two parents using Kaiser Window,
Figure 7: Magnitude Response of FIR Filter using two Parents GA and ANN. We have obtained various outputs by changing
at 200 generations with 3 attempts the generations and attempts. It has been observed that a
better response is achieved when three parents are used
instead of two. Best response is obtained in figure (7),(8),(9)
and (10),where 200 generations are taken with three attempts.
With the help of GA, the number of operations in design
process is reduced and coefficient calculation is easily done.
REFERENCES
[1] S. Haykins, Neural Networks A comprehensive foundation, Prentice
Hall of India Private Limited, New Delhi, (2003).
[2] Neha Aggarwal, Sheenu Thapar,Parmindar kaur design a low pass FIR
low pass filter using particle swarm optimization Based ArtificialNeural
Figure 8: Magnitude Response of FIR Filter using three network (IJETTCS) vol 1 Issue 4 ,December 2012.
Parents at 200 generations with 3 attempts [3] Jasdeep singh,charanjit singh Design of Low pass FIR filter by using
(GRNN) (IJARCSSE) vol 3 issue 10 October 2013
[4] Avci K., and Nacaroglu A., A New Window Based on Exponential
Function, Proc. Of 7.th International Conference
COMMUNICATIONS 2008, 63-66, Bucharest, Romania, 2008.
[5] Saramaki, T., A class of window functions with nearly minimum side
lobe energy for designing FIR filters, inproc. IEEE Int. Symp.Circuits
and systems (ISCAS89).359-362, Portland, Ore, USA, 1989.
[6] Kaiser J.F., and Schafer, R.W., On the use of the I0-sinhwindow for
spectrum analysis, IEEE Trans. Acoustic, Speech, and Signal
Processing, 28(1), 105-107, 1980.
[7] Kaiser, J.F., Non recursive digital filter design using I0-sinh window
function, in proc. IEEE Int. Symp. Circuits and systems (ISCAS74).
20-23, San Francisco, Calif, USA, 1974.
[8] Bergen S. W. A., and Antoniou A. Design of Ultra spherical Window
Figure 9:Magnitude Response of FIR Filter using two Parents Functions with Prescribed Spectral Characteristics EURASIP Journal
at 200 generations with 3 attempts on Applied Signal Processing , no.13, pp.2053-2065, 2004.
[9] Genetic Algorithms in search, optimization and Machine Learning By
David E. Goldberg.
[10] Teaching Genetic Algorithm using MATLAB, Y.J. Cao and Q.H. Wu.
Int. J. Elect. Enging. Educ., Vol. 36, pp. 139153. Manchester
U.P.,1999. Printed in Great Britain
[11] Ajoy Kumar Dey, A Method of Genetic Algorithm (GA) for FIR Filter
Construction, Vol. 1, pp. 87-90, Dec 2010
[12] Design of FIR Filter using Genetic Algorithm, Samrat Banerjee,
Sriparna Dey, Supriya Dhabal, IJETR, Volume-3, Issue-6, June 2015
[13] T. Saramaki, Finite impulse response filter design, Handbook for
Digital Signal Processing, S. K. Mitra and J. F. Kaiser, Eds.,Wiley, New
York, NY, USA, (1993).
[14] D. F. Spechtand P. D. Shapiro, Training speed comparison of
probabilistic neural networks with back-propagation networks, Proc.
Int. Neural Network Conf.(Paris, France), vol. 1,(1990) July, pp.
Figure 10: Magnitude Response of FIR Filter using three 440-443.
Parents at 200 generations with 3 attempts [15] P. Burrascano, Learning vector quantization for the probabilistic
neural network, IEEE Trans. Neural Networks, vol. 2,(1991)July, pp.
458-461.
VII. CONCLUSION [16] H.B. Celikoglu,Application of radial basis function and generalized
The proposed technique achieves the optimum number of regression neural networks in non-linear utility function specification
for travel mode choice modelling, Math Compute Model, vol. 44,
coefficients required to get the desired frequency response (2006), pp. 640-58.
with the optimum word length. In this present work, FIR filter
is designed using Kaiser Window, GA and ANN. The Vikash Kumar, Department of Electronics & Communication, M.Tech
response is studied by keeping values of fixed order, Scholar, Kanpur Institute of Technology, Kanpur, India.
Mr. Vaibhav Purwar, Assistant Professor, Department of Electronics
crossover probability and mutation probability. From the
& Communication, Kanpur Institute of Technology, Kanpur, India
15 www.erpublication.org