[go: up one dir, main page]
Scribd
Upload
20 views2 pages

Week05 Assignment05 Solution

The document outlines solutions for a Soft Computing Techniques assignment, focusing on genetic algorithms and selection methods. Key concepts include mutation probability, roulette wheel selection, crossover techniques, and expected counts of individuals based on fitness values. It provides detailed calculations and examples for various selection methods and crossover operations.

Uploaded by

AJ - The PES Lover
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
20 views2 pages

Week05 Assignment05 Solution

The document outlines solutions for a Soft Computing Techniques assignment, focusing on genetic algorithms and selection methods. Key concepts include mutation probability, roulette wheel selection, crossover techniques, and expected counts of individuals based on fitness values. It provides detailed calculations and examples for various selection methods and crossover operations.

Uploaded by

AJ - The PES Lover
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/ 2

Soft Computing Techniques

Week-05 Assignment-05 (Solution)

1. (c). Low mutation probability ensures stability in the evolution process.

2. (a). Roulette wheel selection method works fine for Uniformly distributed fitness values.

3. (a) and (c). The selection pressure is inversely proportional to the population diversity.

4. 0.1, range is 0.09 to 0.11. We know that in Roulette wheel selection method, probability of selecting
an individual is given by,
Fitness of individual i
Pi =
Total fitness of population
10
=⇒ P =
100
=⇒ P = 0.1

5. (b). Using precedence-preservation order crossover, in O1 we will start with P1 but the random vector
says 2 so in O1 the value of P2, which is 6, will be written and in P1 we will cross 6 i.e.,

Random Vector 2 1 1 2 2 1 2 2 1
P1 2 4 3 6 5 8 7 1 9
P2 6 3 5 2 1 7 4 9 8
O1 6

Next we have 1 in random vector, so 2 from P1 will be written in O1 and 2 will be crossed in P2 i.e.,

Random Vector 2 1 1 2 2 1 2 2 1
P1 2 4 3 6 5 8 7 1 9
P2 6 3 5 2 1 7 4 9 8
O1 6 2

Similarly, after some steps, we will get,

O1 6 2 4 3 5 8 1 7 9

6. (c).

Individual fit-value prob. cumulative prob.


1 8 0.1 0.1
2 16 0.2 0.3
3 24 0.3 0.6
4 32 0.4 1.0

Sum of fit-values = 80
∴ R = 0.45 ∈ [0.3, 0.6].
=⇒ 3rd individual
7. 0.4, range is 0.39 to 0.41.

fi
Individual fit-value P
fi

1 12 0.13
2 18 0.2
3 24 0.26
4 36 0.4

Now, expected count of the individual with fitness value 36 is given by,
fi
Expected count = N × P
fi
=⇒ Expected count = 2 × 0.2
=⇒ Expected count = 0.4

8. 1, range is 0.99 to 1.01. N = 6 → population size

fP
i (x)
Individual Fitness Value fi Expected Count Actual Count

1 5 0.05 0.30 x
2 25 0.25 1.5 2
3 10 0.10 0.6 1
4 30 0.30 1.8 2
5 20 0.20 1.2 1 (Answer)
6 10 0.10 0.6 x

So, the actual count of individual with fitness value 20 is 1.

9. (b). In the Tournament selection, the selection pressure is very high.

10. (c). In cycle crossover, we first write the cycle values as it is in the offspring O1 and O2 i.e.,

P1 1 2 3 4 5 6 7 8
P2 8 5 2 1 3 6 4 7
O1 1 4 7 8
O2 8 1 4 7

Now, we will swap the values between parents i.e.,

P1 1 2 3 4 5 6 7 8
P2 8 5 2 1 3 6 4 7
O1 1 5 2 4 3 6 7 8
O2 8 2 3 1 5 6 4 7

You might also like