0% found this document useful (0 votes)
18 views12 pages

Genetic Algorithm for Function Maximization

Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
18 views12 pages

Genetic Algorithm for Function Maximization

Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Genetic algorithm

example
Consider the function of maximizing the function f(x) = x²

where x in permitted to vary between 0 to 31

Select encoding technique:

Using a five-bit binary integer, numbers between 0 (00000) and 31 (11111) can be
obtained
● Select Initial Population

● To start with, select initial population are random.

● Here initial population of size 4 is chosen, but any number of


populations can be selected based on the requirement and
application.
String o Initial X value Fitness prob %prob Expected Actual
popula count count
tion f(x)=x^2

1 01100 12 144

m 2 11001 25 625

e 3 00101 5 25
um 4 10011 19 361

sum

average

maximum
String o Initial X value Fitness prob %prob Expecte Actual
populatio d count count
n f(x)=x^2

1 01100 12 144

2 11001 25 625

3 00101 5 25

4 10011 19 361

sum 1155

average 288.75

maximu 625
m
String o Initial X value Fitness prob %prob Expe
populatio d cou
We need to maximize the n f(x)=x^2
value 625 which we got from
initial population 1 01100 12 144

We need to select some of 2 11001 25 625


these particular solutions and 3 00101 5 25
then we need to apply
remaining steps crossover 4 10011 19 361
and mutation sum 1155
For selection we need to average 288.75
calculate the probability of
these chromosomes maximu 625
m
Calculate the fitness value
To calculate the probability use following formula

For 12 prob=144/1155=0.1247

For 25 prob=625/1125=0.5411
String o Initial X value Fitness prob %prob Expecte Ac
populatio d count co
Then calculate sum, n f(x)=x^2

average, 1 01100 12 144 0.1247 12.47

maximum 2 11001 25 625 0.5411 54.11

3 00101 5 25 0.0216 02.16

4 10011 19 361 0.3126 31.26

sum 1155 1.0 100

average 288.75 0.25 25

maximu 625 0.5411 54.11


m
Calculate the expected count
Formula to calculate expected count

For 12 exp count=144/288.75=0.4987


String o Initial X value Fitness prob %prob Expecte Actual
populatio d count count
n f(x)=x^2

1 01100 12 144 0.1247 12.47 0.4987 1

2 11001 25 625 0.5411 54.11 2.1645 2

3 00101 5 25 0.0216 02.16 0.0865 0

4 10011 19 361 0.3126 31.26 1.250 1

sum 1155 1.0 100 4 4

average 288.75 0.25 25 1 1

maximu 625 0.5411 54.11 2.1645 2


m
Actual count indicates no of times chromosome will be selected,

5 will not be selected for next step


String o Mating Crossov Offsprin x-value Fitness Mutatio x-value Fitness
pool er point g after f(x)=x^2 n f(x)=x^2
crossov
er

1 01100 4 01101 13 169 11101 29 841

2 11001 4 11000 24 576 11000 24 576

3 11001 2 11011 27 729 11011 27 729

4 10011 2 10001 17 289 10100 20 400

sum 1763 2546

averag 440.75 636.5


e

maximu 729 841


m

You might also like