Table 4.

The classification accuracy (%) from subject A1 to subject A9 for different numbers of augmentation samples, where $N_{aug}$ denotes the number of fake samples introduced in the training set and A1–A9 denotes nine different subjects.

$N_{aug}$	A1	A2	A3	A4	A5	A6	A7	A8	A9	Mean	Std
0	65.51	45.18	78.62	53.58	55.64	56.03	71.28	75.02	70.78	63.52	10.70
500	74.01	48.78	80.97	60.51	64.40	57.56	74.45	80.07	76.04	68.53	10.55
1,000	77.32	48.69	81.55	61.64	66.69	58.00	77.10	80.12	78.01	69.90	10.97
2000	77.95	50.37	81.94	63.74	67.35	57.03	79.30	83.88	80.24	71.31	11.42
3,000	79.60	54.25	83.84	60.93	70.54	62.18	79.94	82.01	81.36	72.82	10.44
4,000	79.60	51.94	85.87	65.24	68.34	61.31	78.39	83.48	81.17	72.82	10.94