Table 2.

Valence classification accuracy obtained using different feature extraction techniques on frequency bands.

Method	$\mathit{\delta }$	$\mathit{\theta }$	$\mathit{\alpha }$	$\mathit{\beta }$	$\mathit{\gamma }$	ALLBAND
DE	80.44%	86.57%	86.46%	74.52%	80.20%	86.87%
RASM	56.71%	56.48%	57.60%	74.19%	70.69%	56.24%
DCAU	70.68%	74.84%	72.35%	74.07%	74.78%	93.20%
DASM	72.59%	78.61%	78.43%	78.48%	80.74%	95.08%
AsMap+CNN	79.61%	85.64%	86.15%	86.83%	86.57%	95.45%

The window size was set to 3 s.