Brown Lindsay, Grundlehner Bernard, Penders Julien
imec / Holst Centre, Eindhoven, the Netherlands.
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:2188-91. doi: 10.1109/IEMBS.2011.6090412.
Intelligent affective computers can have many medical and non-medical applications. However today's affective computers are limited in scope by their transferability to other application environments or that they monitor only one aspect of physiological emotion expression. Here, the use of a wireless EEG system, which can be implemented in a body area network, is used to investigate the potential of monitoring emotional valence in EEG, for application in real-life situations. The results show 82% accuracy for automatic classification of positive, negative and neutral valence based on film clip viewing, using features containing information on both the frequency content of the EEG and how this changes over time.
智能情感计算机可拥有众多医学和非医学应用。然而，当今的情感计算机在范围上受到限制，要么是因为它们难以转移到其他应用环境，要么是因为它们仅监测生理情绪表达的一个方面。在此，使用一种可在人体区域网络中实现的无线脑电图（EEG）系统，来研究在脑电图中监测情绪效价的潜力，以便应用于现实生活场景。结果表明，基于观看电影片段，利用包含脑电图频率内容及其随时间变化信息的特征，对正性、负性和中性效价进行自动分类的准确率达82%。
