Fusion of Motif- and Spectrum-Related Features for Improved EEG-Based Emotion Recognition

<table class="table-group" id="tab8"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Fusion methods</td><td class="align_center">Valence BACC</td><td class="align_center">Arousal BACC</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">Feature</td><td class="align_center">0.6010</td><td class="align_center">0.5645</td></tr><tr><td class="align_left">Score</td><td class="align_center">0.5875</td><td class="align_center">0.5807</td></tr><tr><td class="align_left">OAF</td><td class="align_center">0.5873</td><td class="align_center">0.5568</td></tr><tr><td class="align_left">Random voting</td><td class="align_center">0.5018</td><td class="align_center">0.5028</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Performance comparison of different fusion methods and a random voting classifier with chance levels.</div>

Computational Intelligence and Neuroscience

tab8

Table 8

Table 8: Fusion of Motif- and Spectrum-Related Features for Improved EEG-Based Emotion Recognition 