A Comparative Analysis of Swarm Intelligence Techniques for Feature Selection in Cancer Classification

Pseudocode 4

Pseudocode for SFLLF.

Generate random population of 𝑃 solutions (frogs);

   Calculate fitness function 𝑓 value of each frog;

    Repeat for specific number of times

      Sort the population 𝑃 in descending order of their fitness;

      Divide 𝑃 into 𝑚 memeplexes;

      Repeat for specific number of iterations

      For each memeplex determine the best and worst frogs 𝑋_𝑏 and 𝑋_𝑤;

      Identify the best frog for the entire population 𝑋_𝑔;

      Improve the worst frog position using 𝑋_𝑤(𝑡+1)=rand()×(𝑋_𝑏(𝑡)−𝑋_𝑤(𝑡))

      If 𝑓(𝑋_𝑤(𝑡+1))<𝑓(𝑋_𝑤(𝑡))

         𝑋_𝑤(𝑡+1)=rand()×(𝑋_𝑔(𝑡)−𝑋_𝑤(𝑡))

         if 𝑓(𝑋_𝑤(𝑡+1)<𝑓(𝑋_𝑤(𝑡))

              Levy∼𝑢=𝑡^−𝜆 and 𝑥_𝑤(𝑡+1)=𝑥_𝑤(𝑡)+𝛼⊕Levy(𝜆)

      end;

      Combine the evolved memeplexes;

    end;

   Present the best frog 𝑋_𝑔

   end;

The symbol ⊕ is an entrywise multiplication. Basically Lévy flights provide a random walk while their random steps are drawn

from a Lévy distribution for large steps.