利用神经网络从心率变异性和皮肤电阻识别人类情绪。
Using neural network to recognize human emotions from heart rate variability and skin resistance.
作者信息
Lee Chung, Yoo S K, Park Yoonj, Kim Namhyun, Jeong Keesam, Lee Byungchae
机构信息
Yonsei University, Seoul, Korea (phone: 822-222-81922; fax: 822-361-9923; e-mail:
出版信息
Conf Proc IEEE Eng Med Biol Soc. 2005;2005:5523-5. doi: 10.1109/IEMBS.2005.1615734.
The purpose of this paper is to estimate emotions using Neural network and the changes in activities of autonomic nervous system(ANS). Since ANS cannot be controlled artificially, we presumed that the changes in emotions would be reflected to the changes in ANS. In order to observe those changes, we provided the subjects with some video clips which can induce a variety of emotions and measured the changes in ANS, especially in Heart Rate Variability(HRV) and in Galvanic Skin Response(GSR). With those analyzed results from the experiments, we established an algorithm based on Neural network, finally we could reach the estimating rate of 80.2%
本文的目的是利用神经网络和自主神经系统（ANS）活动的变化来估计情绪。由于自主神经系统无法人为控制，我们推测情绪的变化会反映在自主神经系统的变化中。为了观察这些变化，我们向受试者提供了一些能够诱发多种情绪的视频片段，并测量了自主神经系统的变化，特别是心率变异性（HRV）和皮肤电反应（GSR）的变化。根据实验的分析结果，我们建立了一种基于神经网络的算法，最终我们能够达到80.2%的估计准确率。
Zotero 插件