Bras Susana, Ferreira Jacqueline, Soares Sandra C, Silva Carlos F
Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:2351-4. doi: 10.1109/EMBC.2015.7318865.
The identification or classification of emotions allows the description of the person's state and, therefore, the inference of their preferences. The basic emotion of disgust, in particular, allows the organism to protect itself against diseases. Usually, the decrease in heart rate is associated with this emotion. As an avoidance behavior, when facing with disgust stimuli, the body reacts with movements, such as muscle contraction, etc. These reactions are evidenced in the electrocardiogram (ECG) as noise responses. In this paper, we propose the amount of ECG noise measured by the noise entropy as a new biomarker in emotion identification, which has been neglected in the literature. Our results showed that the noise entropy was able to discriminate between disgust, fear and neutral conditions in 88% (p<;0.05). It was also evidenced in this dataset that the median noise entropy in disgust was higher than in neutral and in fear conditions.
情绪的识别或分类有助于描述人的状态，进而推断他们的偏好。特别是厌恶这种基本情绪，能使机体保护自身免受疾病侵害。通常，心率下降与这种情绪相关。作为一种回避行为，当面对厌恶刺激时，身体会通过肌肉收缩等动作做出反应。这些反应在心电图（ECG）中表现为噪声响应。在本文中，我们提出将通过噪声熵测量的心电图噪声量作为情绪识别中的一种新生物标志物，而这一点在文献中一直被忽视。我们的结果表明，噪声熵能够在88%的情况下（p<0.05）区分厌恶、恐惧和中性状态。在该数据集中还证实，厌恶状态下的噪声熵中位数高于中性和恐惧状态。
