(R3)(RRC)

download PDF with first 40 pages
from my latest eBook
if you need more operators click here

Keywords
schema, similarity

Motivation
●   Offspring generation from a similarity set of the parents.

Source text
● Radcliffe N.J.  (1991), Forma Analysis and Random Respectful Recombination, in Proceedings of the Fourth International Conference on Genetic Algorithms, pp. 222-229
WEB:     http://users.breathe.com/njr/formaPapers.html
            http://citeseer.ist.psu.edu/radcliffe91formal.html

Read also
●  Watson R.A., Pollack J.B.  (2000), Recombination Without Respect: Schema Combination and Disruption in Genetic Algorithm Crossover, in Proceedings of GECCO 2000, Morgan Kaufman, pp. 112-119
WEB:     http://citeseer.ifi.unizh.ch/watson00recombination.html
            http://citeseer.ist.psu.edu/watson00recombination.html
●    Ozugur T.  (2005), Hierarchical Provisioning for Cellular networks, in IEEE Transactions on Wireless Communications, vol. 4(2), pp. 775-791
WEB:      http://ieeexplore.ieee.org/xpl/abs_free.jsp?arNumber=1413243
●  Nomura T.  (1997), An Analysis on Crossovers for Real Number Chromosomes in an Infinite Population Size, ATR Human Information Processing Research Laboratories, Evolutionary Systems Department
WEB:     http://citeseer.ifi.unizh.ch/62577.html
            http://citeseer.ist.psu.edu/62577.html

See also
●    Hierarchical Crossover
●    Disrespectful Crossover
●    Asymmetric Two-point Crossover
●    Variation of Asymmetric Two-point Crossover
●    Homologous Crossover
●    Schema-Based Crossover
●    Adaptive Probability Crossover-4

Algorithm
1.     select two parents A^(t) and B^(t) from a parent pool

2.     create a similarity vector S^AB=(s₁^AB,...,s_n^AB) as follows:

3.              for i = 1 to n do

4.                              if a_i^(t)=b_i^(t) then

5.                              s_i^AB=a_i^(t)

6.                              else

7.                              s_i^AB=NULL

8.                              end if

9.              end do

10.  create two offspring C^(t+1) and D^(t+1)  as follows:

11.           for i = 1 to n do

12.                           if s_i^AB=1 then

13.                           c_i^(t+1)=1 

14.                           d_i^(t+1)=1   

15.                           else if s_i^AB=0 then

16.                           c_i^(t+1)=0 

17.                           d_i^(t+1)=0  

18.                           else if s_i^AB=NULL then

19.                           choose a uniform random real number u from interval
                           <0,1>

20.                                           if u≤0.5 then

21.                                           c_i^(t+1)=1 

22.                                           else

23.                                           c_i^(t+1)=0 

24.                                           end if

25.                           choose a uniform random real number u from interval
                            <0,1> 

26.                                           if u≤0.5 then

27.                                           d_i^(t+1)=1 

28.                                           else

29.                                           d_i^(t+1)=0   

30.                                           end if

31.                           end if

32.           end do

Comments
●   The R3 algorithm duplicates genes of parents in an offspring at every position at which they are identical (rows: 12-17). At positions where  values of the parent genes are different they are determined at random (rows: 18-31).

Experiment domains
●    n/a

Compared to
●    n/a