Parent selection in genetic algorithms, Lecture notes of Computer Science

Download Parent selection in genetic algorithms and more Lecture notes Computer Science in PDF only on Docsity!

Parent Selection

Roulette Wheel Selection (RWS)

• it gives to each individual i of the current population a probability

p(i) of being selected [10], proportional to its fitness f (i)

• (^) Higher the fitness of individual, higher the chances of getting

selected. The principle of roulette selection follows a linear search

through a roulette wheel with the slots in the wheel weighted in

proportion to the individual’s fitness values.

• Note that a well-known drawback of this technique is the risk of

premature convergence of the GA to a local optimum, due to the

possible presence of a dominant individual that always wins the

competition and is selected as a parent

Stochastic Universal Sampling (SUS)

• (^) The SUS [8] is a variant of RWS aimed at reducing the

risk of premature convergence

Sumf(1); deltaf; j 0 ;

Do{

• If (deltaSum) {
• select the sth individual;
• delta delta Sum ; }

else {

• ss 1 ;
• ISumSumf(j) ;

} while (sn)

LRS_ pseudo-code {

 Calculate the sum v  1 ; n 2.

 For each individual 1 kn do {

• Generate a random number 0,v; - Foreach 1 indo{
• If(p(i)){
• Select the ith individual; - Break;

Exponential Rank Selection (ERS)

• (^) The ERS [10] is based on the same principle as LRS, but

it differs from LRS by the probability of selecting each

individual. For ERS, this probability is given by the

expression:

• (^) p(i) = 1.0 * exp/ (rang(i)/c)
• (^) C = n2(n-1)/ 6 *(n-1) +n

Once the n probabilities are computed, the rest of the

method can be described by the following pseudo-code:

Tournament Selection (TOS)

Tournament selection [11] is a variant of rank-based

selection methods. Its principle consists in randomly

selecting a set of k individuals. These individuals are

then ranked according to their relative fitness and the

fittest individual is selected for reproduction. The whole

process is repeated n times for the entire population.

TOS_ pseudo-code { Create a table t where the n individuals are

placed in a randomly chosen order

For k=1 to n do {

• for s=1 to n do {
  • k1=t(s);
• For m=1 to ndo{
  • k2 = t(s+m);
• If ( f(k1)>f(k2)) the select k1 }// end for m

else select k2 ;

• s=s+r;

} // end for s

• (^) } // end for k

   } 

Order the n individuals of P(t) according to their fitness;

Set the portion p of individuals to select (e.g.10%<=

p<=50%);

Sp= int(n*p)// selection pressure; Select the first sp

individuals;

}

Sources : Selection Methods for

Genetic Algorithms – Khalid Jebari

Review of Selection Methods in

Genetic Algorithms Nisha Saini