Emotion Recognition Based on EEG Using Generative Adversarial Nets and Convolutional Neural Network

Table 7

The recognition accuracy (%) of the two models in four classification tasks before and after data augmentation.

Subject	Case 1		Case 2
	FBCCNN	FBSCNN	FBCCNN	FBSCNN
S01	65.08	59.23	76.00	68.87
S02	66.23	60.38	77.16	70.02
S04	59.64	53.79	70.57	63.43
S06	60.10	57.46	71.03	67.10
S07	60.86	55.01	71.78	64.65
S08	66.43	60.58	77.36	70.22
S09	64.90	59.05	75.83	68.69
S10	65.34	59.49	76.27	69.13
S11	66.22	60.37	77.15	70.00
S17	70.18	64.33	81.11	73.97
S18	58.06	52.21	68.99	61.85
S22	60.32	54.47	71.25	64.11
Average recognition accuracy results across subjects
Across subjects	55.87	52.34	70.34	66.90