Table 4.

Four-class classification accuracy obtained using different feature extraction techniques on frequency bands.

Method	$\mathit{\delta }$	$\mathit{\theta }$	$\mathit{\alpha }$	$\mathit{\beta }$	$\mathit{\gamma }$	ALLBAND
DE	70.23%	80.33%	80.89%	76.76%	79.31%	86.30%
RASM	30.97%	30.23%	47.15%	62.11%	59.11%	38.61%
DCAU	53.20%	62.71%	59.47%	58.87%	61.89%	90.48%
DASM	60.38%	69.65%	67.08%	67.57%	70.51%	92.23%
AsMap+CNN	67.86%	79.43%	79.15%	81.66%	82.16%	93.41%

The window size was set to 3 s.