Extracting a Novel Emotional EEG Topographic Map Based on a Stacked Autoencoder Network

Table 1

Features extracted in the SAETM algorithm.

Channels	Features	Formula	Feature index
Fp1, AF3, F3, F7, FC5, FC1, C3, T7, CP5, CP1, P3, P7, PO3, O1, Oz, Pz, Fp2, AF4, Fz, F4, F8, FC6, FC2, Cz, C4, T8, CP6, CP2, P4, P8, PO4, and O2	EEG power of sub-bands: Theta (4–8 Hz), alpha (8–12 Hz), beta (12–30 Hz), gamma (30–45 Hz)-average PSD		No. 1–128 (4 features 32 channels)
		Form a time series of data
	Mean		No. 129–321 (6 features 32 channels)
		Form a time series of data
	Standard deviation
		Form a time series of data
	Zero-crossing rate
		Form a time series of data
	Fractal dimension	where the variable stands for the number of measurement units, for the scaling factor, and for the fractal dimension
	Approximate entropy	1: Form a time series of data
		2: Form a sequence of vectors for fix and real number
		3: Use the sequence to construct, for each
		4:
		5: ApEn =
		Correlation dimension		For any set of points in an -dimensional space
	where is the total number of pairs of points, which have a distance between them that is less than distance