Uniformity-Comprehensive Multiobjective Optimization Evolutionary Algorithm Based on Machine Learning

Table 3

The IGD comparison results of MOEA-UCML with six traditional multiobjective optimization algorithms on the WFG problem sets.

Problem	CCGDE3	GDE3	HypE	MOEA/D	MOEA/D-DE	NSGAII	MOEA-UCML
WFG1	1.7336e + 0 (1.20e − 1)−	1.6986e + 0 (4.30e − 2)−	1.0326e + 0 (8.60e − 2)−	6.8356e − 1 (9.47e − 2)−	1.4705e + 0 (5.63e − 2)−	5.6150e − 1 (6.58e − 2)−	4.9263e − 1 (7.96e − 2)
WFG2	4.1103e − 1 (5.95e − 2)−	2.8494e − 1 (1.35e − 2)−	2.8632e − 1 (7.96e − 3)−	3.2244e − 1 (6.32e − 2)−	3.6277e − 1 (2.33e − 2)−	2.2001e − 1 (7.28e − 3)	2.2624e − 1 (1.00e − 2)
WFG3	4.0099e − 1 (5.65e − 2)−	3.5928e − 1 (2.58e − 2)−	3.1067e − 2 (3.03e − 3)+	3.1744e − 1 (9.29e − 2)−	2.7073e − 1 (2.60e − 2)−	1.2346e − 1 (1.67e − 2)−	1.1915e − 1 (1.60e − 2)
WFG4	3.5323e − 1 (2.43e − 2)−	3.5333e − 1 (1.43e − 2)−	2.6839e − 1 (1.12e − 2)+	2.9518e − 1 (1.27e − 2)−	3.9702e − 1 (1.02e − 2)−	2.8109e − 1 (1.10e − 2)−	2.7556e − 1 (9.68e − 3)
WFG5	3.8142e − 1 (1.81e − 2)−	2.7836e − 1 (1.06e − 2)	3.0093e − 1 (1.38e − 2)−	2.7299e − 1 (7.25e − 3)+	3.3684e − 1 (3.72e − 3)−	2.8423e − 1 (8.75e − 3)−	2.7339e − 1 (9.38e − 3)
WFG6	4.1809e − 1 (4.43e − 2)−	3.1899e − 1 (2.07e − 2)−	2.9994e − 1 (1.40e − 2)−	2.9172e − 1 (2.74e − 2)−	3.2113e − 1 (4.16e − 2)−	2.6845e − 1 (1.29e − 2)−	2.6029e − 1 (1.91e − 2)
WFG7	3.3425e − 1 (2.15e − 2)−	2.9632e − 1 (9.29e − 3)−	3.2576e − 1 (1.47e − 2)−	3.2500e − 1 (4.56e − 2)−	2.4840e − 1 (6.52e − 3)−	2.0655e − 1 (6.52e − 3)−	2.0147e − 1 (5.02e − 3)
WFG8	4.5156e − 1 (1.95e − 2)−	4.0750e − 1 (1.19e − 2)−	3.3085e − 1 (1.00e − 2)−	3.1976e − 1 (1.93e − 2)	3.5242e − 1 (1.27e − 2)−	3.1619e − 1 (6.25e − 3)	3.1162e − 1 (7.98e − 3)
WFG9	3.0796e − 1 (4.15e − 2)−	3.4566e − 1 (8.10e − 3)−	2.8404e − 1 (1.48e − 2)−	2.8369e − 1 (7.06e − 2)−	2.2949e − 1 (4.69e − 3)−	2.0442e − 1 (6.31e − 3)	2.0381e − 1 (7.84e − 3)
	9/0/0	8/0/1	7/2/0	7/1/1	9/0/0	6/0/3