0% found this document useful (0 votes)
4 views

Week06_Assignment06_Solution

The document outlines solutions to assignments related to soft computing techniques, focusing on function minimization and genetic algorithms. It includes calculations for fitness values, one-point crossover operations, and selection probabilities based on given populations. Additionally, it discusses encoding and evaluating chromosomes within specified ranges.
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)
4 views

Week06_Assignment06_Solution

The document outlines solutions to assignments related to soft computing techniques, focusing on function minimization and genetic algorithms. It includes calculations for fitness values, one-point crossover operations, and selection probabilities based on given populations. Additionally, it discusses encoding and evaluating chromosomes within specified ranges.
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
You are on page 1/ 3

Soft Computing Techniques

Week-06 Assignment-06 (Solution)

1. 5, range is 4.99 to 5.01. Given function is f (x) = (x − 4)2 and x ∈ [0, 31], ϵ = 1.0. Also, we have,

b−a
2n − 1 ≥
ϵ
31 −0
=⇒ 2n − 1 ≥
1
=⇒ 2n ≥32
=⇒ n ≥ 5

which gives n = 5.

2. (c). For the given data we have,

Population Fitness value


2 f (2) = (2 − 4)2 = 4
7 f (7) = (7 − 4)2 = 9
11 f (11) = (11 − 4)2 = 49
30 f (30) = (30 − 4)2 = 676
31 f (31) = (31 − 4)2 = 729

Since we have to minimize the given function, so 2 is the fittest.

3. (b). 2 and 7 are represented by 00010 and 00111, when we apply one-point crossover at the third
location we get,

2 :000|10
7 :001|11
O1 :000|11
O2 :001|10

4. (a). The phenotypes will be given by,

00011 = 21 + 20
=⇒ 00011 = 3
00110 = 22 + 21
=⇒ 00110 = 6
5. (d). 2 and 11 are represented by 00010 and 01011, when we apply one-point crossover at the second
location we get,

2 :00|010
11 :01|011
O3 :00|011
O4 :01|010

6. (a). The phenotypes will be given by,

00011 = 21 + 20
=⇒ 00011 = 3
01010 = 23 + 21
=⇒ 00110 = 10

7. (d). Given the fitness function f (x) which is equal to numbers of ones in the bit string x, so for the
given population we have,

Population Fitness value


0000 1111 4
0001 1001 3
0010 1011 4
0011 1110 5

4+3+4+5
8. (b). We know that the average value is given by, Average = 4 =4
So, we get
Fitness value
Population Fitness value Expected count = Average
4
0000 1111 4 4 =1
3
0001 1001 3 4
4
0010 1011 4 4 =1
5
0011 1110 5 4

9. (d). The sum of the population is,

Sum = 4 + 3 + 4 + 5
=⇒ Sum = 16

So, the selection probability is


Fitness value
Population Fitness value Selection Probability = Sum
4
0000 1111 4 16 = 0.25
3
0001 1001 3 16 = 0.1875
4
0010 1011 4 16 = 0.25
5
0011 1110 5 16 = 0.3125
10. 0.10, range is 0.09 to 0.11.
We have the binary encoded value of chromosome 01100101 which is,

01100101 = 26 + 25 + 22 + 20
=⇒ 01100101 = 101

Let X = 101 ∈
/ [0, 25.5], so we will use a formula to make X lie inside the given interval, given by
n b−a o
x=a+ X
2n − 1

Here, we have 8 bits =⇒ n = 8 and the given interval is [0, 25.5] =⇒ b = 25.5 and a=0. Then the
above formula becomes,
n 25.5 − 0 o
x=0+ × 101
28 − 1
n 25.5 o
x= × 101
255
=⇒ x = 10.1

Now, the functional value at x = 10.1 is given by,


200
y = 0.1x2 +
x
200
=⇒ y = 0.1 × (10.1)2 +
10.1
=⇒ y ≈ 30

Then the expected count of the given chromosome is,


y
E.C. = P
yi
30
=⇒ E.C. =
300
=⇒ E.C. = 0.1

You might also like