Table 6.

Classification accuracy of the methods for the BCI competition IV dataset 1 (baseline: 74.5 ± 4.0%).

	Ratio	Accuracy% (Mean ± std. dev.)
Method		1:1	1:3	1:5	1:7	1:9
CNN-GT		70.5 ± 2.0	68.5 ± 3.2	69.7 ± 1.8	63.5 ± 2.1	68.5 ± 3.7
CNN-NA		76.5 ± 2.2	77.8 ± 3.5	72.1 ± 5.2	69.8 ± 3.5	70.3 ± 3.9
CNN-AE		75.6 ± 3.0	78.2 ± 1.8	77.6 ± 3.5	72.0 ± 3.7	68.2 ± 5.2
CNN-VAE		77.8 ± 3.4	78.2 ± 2.2	75.4 ± 3.6	73.1 ± 2.2	70.8 ± 3.9
CNN-DCGAN		82.5 ± 1.7	83.2 ± 3.5	80.9 ± 2.1	75.5 ± 4.6	78.6 ± 2.6