Short-term analysis of heart rate variability for emotion recognition via a wearable ECG device

Emotion influences human health significantly. Because of the improvement of wearable device, daily electrocardiogram (ECG) detection became accessible. In this pilot study, we presented a weightless and wearable ECG device to collect ECG signal. Movie clips method has been designed to induce 4 kinds of emotion states. 90 sec corresponding ECG signal have been measured in the end of video stimulus. Physiological features from various analysis domains, including time, frequency, and statistic analysis are proposed in order to find the best emotion-relevant features. Finally, two features were reported in this study to evaluate human's emotion.