An Improved Grey Wolf Optimization Strategy Enhanced SVM and Its Application in Predicting the Second Major

Algorithm 1

Pseudocode of the IGWO algorithm.

Begin

Initialize the parameters popsize, maxiter, n, pos, and flag where

popsize: size of population,

maxiter: maximum number of iterations,

: total number of features,

pos: position of grey wolf,

flag: mark vector of features;

Generate the initial positions of grey wolves using binary PSO;

Initialize , , and ;

for  

 for  

  if   > 0.5

      ;

  else

    ;

  end if

  end for

end for

Calculate the fitness of grey wolves with selected features;

alpha = the grey wolf with the first maximum fitness;

beta = the grey wolf with the second maximum fitness;

delta = the grey wolf with the third maximum fitness;

while  k < maxiter

   for  

   Update the position of the current grey wolf;

   end for

   for  

    for  

      if  

         ;

      else

         ;

      end if

    end for

  end for

  Update a, , and ;

  Calculate the fitness of grey wolves with selected features;

  Update alpha, beta, and delta;

  ;

end while

Return the selected features of alpha as the optimal feature subset;

End