Novel Crow Swarm Optimization Algorithm and Selection Approach for Optimal Deep Learning COVID-19 Diagnostic Model

Algorithm 2

Pseudocode of CSO.

(1)	Maximum_number_of_iterations = 1000.
(2)	Initialize population of 15 solutions, and each solution is of length 11 (9 for the metrics and the angle and speed).
(3)	Initialize speed S and angle Ɵ, where (S ∊ [−6, 6]), (Ɵ ∊ [45, 135]).
(4)	Calculate the fitness (general average) for all solutions, using equation (10)
(5)	Select the best value of the general average and store it in CurrentBest.
(5)	t = 1.
(6)	While (t ≤ maximum_number_of_iterations)
(7)	Update the position of all solutions, using the following:
(8)	Update the fitness of all solutions.
(9)	Select the best value of fitness and store it in NewBest.
(10)	Update CurrentBest:
	if NewBest is better than CurrentBest then CuurentBest = NewBest.
(11)	Update the angle of solutions using the following:
	Ɵi + 1=(Ɵi + Ɵbest)/2
(12)	t = t + 1.
(13)	End while.
(14)	Return the solution that has the best fitness.