Uniformity-Comprehensive Multiobjective Optimization Evolutionary Algorithm Based on Machine Learning

Algorithm 3

Mutation NN.

	Input: (population), (number of decision variables), M (number of targets), gen3 (number of third stage iterations), k (cluster)
	Output: (phase 3 population).
(1)	⟵ Crossover work/ Training neural network /
(2)	NET ⟵ train (, , Layers, Options)
(3)	[C, Num] ⟵ K-means (, k)/K-means finds the most inhomogeneous cluster /
(4)	for  ⟵ 1 to size (C) − 1 do
(5)	C ⟵ predict (NET, C);
(6)	C′ ⟵
(7)	C ⟵ max (0, min (1, C′))
(8)	Mutation ⟵ Calculate the Mutation by using equation (11)
(9)	end for
(10)	⟵  ( (Num)! = C (Num)) ∪ C/ Replace the variant part /
(11)	return