Figure 3 | Scientific Reports

Figure 3

From: Two-dimensional CNN-based distinction of human emotions from EEG channels selected by multi-objective evolutionary algorithm

Figure 3

Left: Average accuracies and standard deviation obtained with EEGNet per each subject for low vs high arousal/valence classification using all the EEG channels from 2, 5 and 10-s signal segments. Right: Accuracies obtained with a single EEGNet model with data from all the subject for low vs high arousal/valence classification using all the EEG channels from 2, 5 and 10-s signal segments.

Back to article page