Table 2 Pseudo-code of the proposed SSA-PSO method.

Input:

The initial solution set X, X=[X_sparrows, X_particle], setting the population size of sparrows and particle swarms, the number of iterations and other parameters, the fitness function F

Output:

X_best

Set1:

sort X_sparrows and X_particle according to F

Set2:

while the number of iterations is not greater than the number of terminations

updates the location of spotters, followers, and scouts

sort X_sparrows according to F

dynamic backward mutation of X_sparrows0

if F(X_sparrows0) > F(X_new)

X_sparrows0 = X_new

else continue

if F(X_sparrows0) < F(X_particle0) then

insert X_sparrows0 into X_particle to become X_particle0

update the position and velocity of X

sort X_particle according to F

X_best= X_particle0

else X_best= X_particle0

end while

Set3:

output X_best