See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/325011628

Comparative Study of Different Selection Techniques in Genetic Algorithm

Article in International Journal of Engineering Science · July 2017

CITATIONS READS
72 4,621

3 authors:

Saneh Lata Saneh Lata Yadav

1 PUBLICATION 72 CITATIONS
Guru Gobind Singh Indraprastha University
8 PUBLICATIONS 115 CITATIONS
SEE PROFILE
SEE PROFILE

Asha Sohal
KR Mangalam University
15 PUBLICATIONS 109 CITATIONS

SEE PROFILE

All content following this page was uploaded by Saneh Lata Yadav on 08 May 2018.

The user has requested enhancement of the downloaded file.

International Journal of Engineering, Science and Mathematics
Vol. 6 Issue 3, July 2017,
ISSN: 2320-0294 Impact Factor: 6.765
Journal Homepage: http://www.ijesm.co.in, Email: [email protected]

Comparative Study of Different Selection Techniques in Genetic Algorithm

Saneh Lata Yadav1
Asha Sohal2
_________________________________________________________________________________________________

Abstract - Genetic Algorithm is search and

optimization technique which has number of steps like
initialization, selection, crossover, mutation and
replacement. Genetic algorithms are optimization search
Keywords: algorithms that maximize or minimizes given functions.
Since GA is heuristic procedures, they are not
guaranteed to find the optimum, but experience has
Genetic Algorithms shown that they are able to find very good solutions for
Selection Techniques a wide range of problems. In this paper focus is given on
Roulette Wheel Selection selection phase of GA and comparison between
Tournament Selection different selection techniques of GA. In selection
operator individual are selected according to their
fitness and chooses those chromosomes in the
population that will be allowed to reproduce, and on
average the fitter chromosomes produce more offspring
than the less fit ones. Researcher has done lot of work in
selection phase of GA. In this paper a number of
selection techniques have been described like roulette
wheel selection, rank selection, tournament selection,
steady state selection, Boltzmann selection and Elitism
selection.

__________________________________________________________________________________________________
Author’s correspondence:
Saneh Lata Yadav Asha Sohal
Assistant Professor Associate Professor
Department of Computer Science & Engineering Department of Computer Science & Engineering
K. R. Mangalam University, Gurgaon K. R. Mangalam University, Gurgaon

__________________________________________________________________________________________________

I. INTRODUCTION

The term "genetic algorithm"' (GA) is applied to any search or optimization algorithm that is based on Darwinian
principles of natural selection. Genetic Algorithm is a population-based search and optimization method which mimics
the process of natural evolution. Genetic Algorithms (GAs) were invented by John Holland in the 1960s and were
developed by Holland (1975) and his students and colleagues at the University of Michigan in the 1960s and the 1970s.
Holland's GA is a method for moving from one population of "chromosomes" to a new population by using a kind of
"natural selection" together with the genetics inspired operators like crossover, mutation, and inversion. A chromosome
contains a group of numbers that completely specifies a candidate solution during the optimization process (Rakesh Kumar
G. G., 2013)[1]. GA is a method for moving from one population of "chromosomes" (e.g., strings of ones and zeros, or
"bits") to a new population by using a kind of "natural selection. The selection operator chooses those chromosomes in
the population that will be allowed to reproduce, and on average the fitter chromosomes produce more offspring than the
less fit ones. Crossover exchanges subparts of two chromosomes, roughly mimicking biological recombination between
two singlechromosome ("haploid") organisms; mutation randomly changes the allele values of some locations in the chromosome; and
inversion reverses the order of a contiguous section of the chromosome, thus rearranging the order in which genes are

174 International Journal of Engineering, Science and Mathematics

http://www.ijesm.co.in, Email: [email protected]
International Journal of Engineering, Science and Mathematics
Vol. 6 Issue 3, July 2017,
ISSN: 2320-0294 Impact Factor: 6.765
Journal Homepage: http://www.ijesm.co.in, Email: [email protected]

arrayed. The selection phase determines which individuals are chosen for mating (reproduction) and how many offspring
each selected individual produces. The main principle of selection strategy is "the better is an individual; the higher is its
chance of being parent." The process that determines which solutions are to be preserved and allowed to reproduce and
which ones deserve to die out [2]. The primary objective of the selection operator is to emphasize the good solutions and
eliminate the bad solutions in a population while keeping the population size constant as shown in figure 1.

Figure 1: Basic Structure of Genetic Algorithm

II. LITERATURE REVIEW

There are different selection techniques in GA which are Roulette wheel selection, Rank selection, Tournament selection,
Steady state selection, Boltzmann selection and Elitism selection.
Some steps in selection Operator
● Identify the good solutions in a population.
● Make multiple copies of the good solutions.
● Eliminate bad solutions from the population so that multiple copies of good solutions can be placed in the
Population.
Roulette Wheel Selection: - Roulette selection is one of the traditional GA selection techniques. Roulette wheel is
the simplest selection technique. In this technique, all the chromosomes in the population are placed on the roulette wheel
according to their fitness value. Each individual is assigned a segment of roulette wheel whose size is proportional to the
value of the fitness of the individual (Noraini Mohd Razali, 2011) [3]. The bigger the fitness value is, the larger the
segment is. Then, the virtual roulette wheel is spinned. The individual corresponding to the segment on which roulette
wheel stops are then selected. The process is repeated until the desired number of individuals is selected. Individuals with
higher fitness have more probability of selection. It can possibly miss the best individuals of a population at certain times.
There is no guarantee that good individuals will find their way (Rakesh Kumar J. , 2012)[4] into next generation. In
proportional roulette wheel, individuals are selected with a probability that is directly proportional to their fitness values i.e.
an individual's selection corresponds to a portion of a roulette wheel. The probabilities of selecting a parent can be seen as

175 International Journal of Engineering, Science and Mathematics

http://www.ijesm.co.in, Email: [email protected]
International Journal of Engineering, Science and Mathematics
Vol. 6 Issue 3, July 2017,
ISSN: 2320-0294 Impact Factor: 6.765
Journal Homepage: http://www.ijesm.co.in, Email: [email protected]

spinning a roulette wheel with the size of the segment for each parent being proportional to its fitness as shown in Table 1.

Population Fitness
1 25.0
2 5.0
3 40.0
4 10.0
5 20.0

Table 1: Ratio between population and fitness

Since the third individual has higher fitness value than any other, it is expected that the roulette-wheel selection will
choose the third individual more than any other individual.

Rank Selection: - The Roulette wheel will have a problem when the fitness values differ very much. If the best
chromosome fitness is 90%, its circumference occupies 90% of Roulette wheel, and then other chromosomes have too
few chances to be selected. Rank Selection ranks the population and every chromosome receives fitness from the ranking.
The worst has fitness 1 and the best has fitness N. It results in slow convergence but prevents too quick convergence. It
also keeps up selection pressure when the fitness variance is low.

Figure 2: Ranking between different chromosomes

It preserves diversity and hence leads to a successful search. In Linear Rank selection, individuals are assigned subjective
fitness based on the rank within the population as in figure 2. The individuals in the population are sorted from best to
worst according to their fitness values. Each individual in the population is assigned a numerical rank based on fitness,
and selection is based on this ranking rather than differences in fitness.

Tournament Selection: - GAs uses a selection mechanism to select individuals from the population to insert into a
mating pool. Individuals from the mating pool are used to generate new offspring, with the resulting offspring forming
the basis of the next generation. A selection mechanism in GA is simply a process that favors the selection of better
individuals in the population for the mating pool. The selection pressure is the degree to which the better individuals are
favored: the higher the select ion pressure, the more the better individuals are favored (S.N. Sivanandam)[5]. This
selection pressure drives the GA to improve the population fitness over succeeding generations. The convergence rate of a
GA is largely determined by the selection pressure, with higher selection pressures resulting in higher convergence rates.
However, if the selection pressure is too low, the convergence rate will be slow, and the GA will unnecessarily take
longer to find the optimal solution. If the selection pressure is too high, there is an increased chance of the GA
prematurely converging to an incorrect (suboptimal) solution. Tournament selection provides selection pressure by holding
a tournament among s competitors, with s being the tournament size. The winner of the tournament is the individual with
the highest fitness of the s tournament competitors. The winner is then inserted into the mating pool. The mating pool,
being comprised of tournament winners, has a higher average fitness than the average population fitness. This fitness

176 International Journal of Engineering, Science and Mathematics

http://www.ijesm.co.in, Email: [email protected]
International Journal of Engineering, Science and Mathematics
Vol. 6 Issue 3, July 2017,
ISSN: 2320-0294 Impact Factor: 6.765
Journal Homepage: http://www.ijesm.co.in, Email: [email protected]

difference provides the selection pressure, which drives the GA to improve the fitness of each succeeding generation.
Increased selection pressure can be provided by simply increasing the tournament size s, as the winner from a larger
tournament will, on average, have a higher fitness than the winner of a smaller tournament (Brad L. Mille r) [6].

Figure 3: Tournament selection using mating pool

The final victor of the competition will always be the fittest chromosome in the population as shown in figure 3. The
more successful the chromosome is in competition, the more often that chromosome is expected to appear in the mating
pool.

Steady State Selection: - In this method, a few good chromosomes are used for creating new offspring in every
iteration. Then some bad chromosomes are removed and the new offspring is placed in their places. The rest of population
migrates to the next generation without going through selection process (Bhattachariya) [7]. Main idea of this selection is
that big part of chromosomes should survive to next generation. In every generation is selected a few (good - with high
fitness) chromosomes for creating a new offspring. Then some (bad - with low fitness) chromosomes are removed and the
new offspring is placed in their place. The rest of population survives to new generation.

Boltzmann Selection: - In Boltzmann selection a continuously varying temperature controls the rate of selection
according to a preset schedule. The temperature starts out high, which means the selection pressure is low. The
temperature is gradually lowered, which gradually increases the selection pressure, thereby allowing the GA to narrow in
more closely to the best part of the search space while maintaining the appropriate degree of diversity.

Elitism Selection: - The idea here is to arrange the chromosomes in the decreasing order according to their fitness
values. Then apply the selection with each two chromosomes in the arranged set. In this way, Genetic Algorithm will be
applied between strong chromosomes or between weak chromosomes. This means there is no chance to apply Genetic
Algorithm between weak and strong chromosomes (Firas Alabsi, 2012) [8].Elitism is a kind of selection in which the best
individual passed to the next generation as such without any modification. Elitism prevents the best individual to undergo
the reproduction process so as to pass them without any modification into next generation.

177 International Journal of Engineering, Science and Mathematics

http://www.ijesm.co.in, Email: [email protected]
 International Journal of Engineering, Science and Mathematics
Vol. 6 Issue 3, July 2017,
ISSN: 2320-0294 Impact Factor: 6.765
Journal Homepage: http://www.ijesm.co.in, Email: [email protected]

III. RESULTS & DISCUSSION

Citation Publication Author and Factor Selection Technique Observations

Year year Considered
for study

(Goldberg 1991 Goldberg, Expected Compared proportional, Ranking and tournament

, 1991)[9] David E., and fitness ratio ranking, tournament and selection is better than proportional
Kalyanmoy and time to steady state selection. selection in terms of
Maintaining steady pressure
Deb converge
toward Convergence. Binary
tournament selection is
recommended over linear ranking
Selection because of its more
efficient time complexity.

(Zhong, 1999 Julstrom, Probability of Studied the computing Tournament selection is better than
2005)[10] Bryant A ith Time efficiency of 2 types of rank based selection, since repeated
chromosome Rank based selection (linear tournament selection is
and exponential),and faster than sorting the population
compared them with and then assigning rank based
Tournament selection Probabilities to them.
method.

(Julstrom, 2005 Zhong, J., Hu, Using 7 Compared Proportionate Tournament selection is more
1999)[11] X., Gu, M., & general test roulette wheel Selection efficient than Proportionate
Zhang functions method and Tournament roulette wheel selection in terms of
selection method. Convergence rate.
(tournament size=6)

(Mashoho 2005 Mashohor, Maximum Compared Deterministic, The ability to reach the maximum
r, Syamsiah, fitness Tournament and fitness with lowest no. of
2005)[12] Jonathan R. Rate of Roulette wheel selection generations is highest in
Evans, and accuracy methods. deterministic. This is followed by
Tughrul Computation
roulette wheel and then tournament
Arslan time
selection.

178 International Journal of Engineering, Science and Mathematics

http://www.ijesm.co.in, Email: [email protected]
International Journal of Engineering, Science and Mathematics
Vol. 6 Issue 3, July 2017,
ISSN: 2320-0294 Impact Factor: 6.765
Journal Homepage: http://www.ijesm.co.in, Email: [email protected]

IV. CONCLUSION

In this paper we have described six types of selection strategy in the GA procedure to find the optimum solution for the
chromosomes and compare the performance in terms of solution quality and number of generations to come out with the
best solution. In Roulette wheel, all the chromosomes in the population are placed on the roulette wheel according to their
fitness value. The virtual roulette wheel is spinned. The process is repeated until the desired number of individuals is
selected. Individuals with higher fitness have more probability of selection. Rank selection ranks the population and every
chromosome receives fitness from the ranking. It results in slow convergence but prevents too quick convergence. In
tournament selection winner of the tournament is the individual with the highest fitness of the s tournament competitors.
The winner is then inserted into the mating pool. In steady state selection some good chromosomes are selected and bad
chromosomes are removed. Boltzmann selection controls the rate of selection by varying temperature. The result shows
that the genetic algorithm with elitism provides more optimal solution and has better convergence speed than the simple
genetic algorithm. All of these selection mechanisms have the same purpose of creating more copies of the individuals
with higher fitness than those with lower fitness. However the selection mechanisms differ in the manner in which they
allocate copies to the fittest individuals. A selection method has the higher selection measure than the other if it makes more
copies of the best individuals thereby eliminating low fit individuals rapidly. A strong selection mechanism reaches
equilibrium faster than a weaker method.

REFERENCES

[1] Rakesh Kumar, Girdhar Go (Rakesh Kumar G. G., 2013)pal, Rajesh Kumar," Hybridization in Genetic Algorithms", an
International Journal of Advanced Research in Computer Science and Software Engineering, Volume 3, Issue 4, April 2013.

[2] Mitchell Melanie," An Introduction to Genetic Algorithms".

[3] Noraini Mohd Razali, John Geraghty," Genetic Algorithm Performance with Different Selection Strategies in Solving TSP",
Proceedings of the World Congress on Engineering 2011 Vol II.

[4] Rakesh Kumar, Jyotishree,"Effect of Polygamy with Selection in Genetic Algorithm", an International Journal of Soft Computing
and Engineering (IJSCE) ISSN: 2231-2307, Volume-2, Issue-1, March 2012.

[5] S.N.Sivanandam, S.N.Deepa," An Introduction to Genetic Algorithms".

[6] Brad L. Mille r, David E. Goldberg," Genetic Algorithms, Tournament Selection, and the Effects of Noise".

[7] Dr. Rajib Kumar Bhattacharjya,"Introduction To Genetic Algorithms".

[8] Firas Alabsi,Reyadh Naoum," Comparison of Selection Methods and Crossover Operations using Steady State Genetic Based
Intrusion Detection System", an Journal of Emerging Trends in Computing and Information Sciences, VOL. 3, NO.7, July 2012.

[9]Goldberg, David E., and Kalyanmoy Deb. "A comparative analysis of selection schemes used in genetic algorithms." Urbana 51
(1991): 61801-2996.

[10] Zhong, Jinghui, et al. "Comparison of performance between different selection strategies on simple genetic algorithms."
Computational Intelligence for Modelling, Control and Automation, 2005 and International Conference on Intelligent Agents, Web
Technologies and
Internet Commerce, International Conference on. Vol. 2. IEEE, 2005.

179 International Journal of Engineering, Science and Mathematics

http://www.ijesm.co.in, Email: [email protected]
 International Journal of Engineering, Science and Mathematics
Vol. 6 Issue 3, July 2017,
ISSN: 2320-0294 Impact Factor: 6.765
Journal Homepage: http://www.ijesm.co.in, Email: [email protected]

[11] Julstrom, Bryant A. "It's all the same to me: Revisiting rank-based probabilities and tournaments." Evolutionary Computation, 1999.
CEC99. Proceedings of the 1999 Congress on. Vol. 2. IEEE, 1999.

[12] Mashohor, Syamsiah, Jonathan R. Evans, and Tughrul Arslan. "Elitist selection schemes for genetic algorithm based printed circuit
board inspection system."Evolutionary Computation, 2005. The 2005 IEEE Congress on. Vol. 2. IEEE, 2005.

180 International Journal of Engineering, Science and Mathematics

http://www.ijesm.co.in, Email: [email protected]

View publication stats