期刊
SENSORS
卷 20, 期 3, 页码 -出版社
MDPI
DOI: 10.3390/s20030866
关键词
emotion classification; physiological signals; machine learning; deep learning; principal components analysis; convolution neural networks
资金
- National Research Foundation of Korea [NRF-2017R1D1A1B03035606]
- Ministry of Trade, Industry and Energy, ROK [10073159]
This study aimed to design an optimal emotion recognition method using multiple physiological signal parameters acquired by bio-signal sensors for improving the accuracy of classifying individual emotional responses. Multiple physiological signals such as respiration (RSP) and heart rate variability (HRV) were acquired in an experiment from 53 participants when six basic emotion states were induced. Two RSP parameters were acquired from a chest-band respiration sensor, and five HRV parameters were acquired from a finger-clip blood volume pulse (BVP) sensor. A newly designed deep-learning model based on a convolutional neural network (CNN) was adopted for detecting the identification accuracy of individual emotions. Additionally, the signal combination of the acquired parameters was proposed to obtain high classification accuracy. Furthermore, a dominant factor influencing the accuracy was found by comparing the relativeness of the parameters, providing a basis for supporting the results of emotion classification. The users of this proposed model will soon be able to improve the emotion recognition model further based on CNN using multimodal physiological signals and their sensors.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据