Optimizing Residual Networks and VGG for Classification of EEG Signals: Identifying Ideal Channels for Emotion Recognition

<div>SEED 3-class emotion recognition accuracy by variants of <i>ResNet18</i> using different subsets of EEG channels. (a) Classification accuracy and the total number of model parameters. (b) Different subsets EEG channels.</div>

Journal of Healthcare Engineering

fig5

Figure 5

Figure 5: Optimizing Residual Networks and VGG for Classification of EEG Signals: Identifying Ideal Channels for Emotion Recognition 