Skip to main content
. 2022 May 19;16:845832. doi: 10.3389/fncel.2022.845832

Table 4.

Comparison of performance of classification methods with power spectra features of EEG2.

SVM ShallowNet EEGNet SWLDA
Leave-one-out validation 78% 71% 43% 36%

The maximum accuracies for each category are in bold.