摘 要:已有许多基于 EEG 信号构建的压力检测模型,这些模型通过刺激材料诱导信号的产生,过程烦琐且难以保证标签的准确度。对此,提出了一种基于 ECG 信号生成标签用于训练 EEG 模型的方法。首先通过实验获取 ECG 数据进行线性拟合;然后同时采集 ECG 和 EEG 信号,用 ECG 生成压力数据并进行离散化;最后使用支持向量机和离散化后的数据训练模型,得到基于 EEG 信号的压力分类模型。在二分类任务下达到了 90.16% 的精度,表明了生成标签和 EEG 模型的有效性。
关键词:ECG;EEG;支持向量机;压力测量
DOI:10.19850/j.cnki.2096-4706.2021.09.024
课题项目:广东省教育厅课题(2019GKTS CX069)
中图分类号:TN911.7 文献标识码:A 文章编号:2096-4706(2021)09-0093-04
Research on Stress Measurement Model Based on ECG and EEG Signals
LIN Ying
(School of Information Engineering,Guangzhou Panyu Polytechnic,Guangzhou 511483,China)
Abstract:There are many stress detection models based on EEG signals. These models induce signal generation by stimulating materials. The process is cumbersome and it is difficult to ensure the accuracy of the label. In this regard,a method of generating tags based on ECG signals for training EEG models is proposed. Firstly,obtain ECG data through experiments for linear fitting;then,collect ECG and EEG signals at the same time,use ECG to generate stress data and discretization;finally use support vector machines and discretized data to train the model to obtain stress classification based on EEG signals model. The accuracy of 90.16% is achieved under the two-class classification task,which shows the effectiveness of the generated label and EEG model.
Keywords:ECG;EEG;support vector machine;pressure measurement
参考文献:
[1] LIAO C Y,CHEN R C,TAI S K. Emotion stress detection using EEG signal and deep learning technologies [C]//2018 IEEE International Conference on Applied System Invention(ICASI). Chiba:IEEE,2018:90-93.
[2] SEGERSTROM S C,MILLER G E. Psychological stress and the human immune system:a meta-analytic study of 30 years of inquiry [J].Psychological Bulletin,2004,130(4):601-630.
[3] 孔令琴,陈飞,赵跃进,等 . 融合心率变异性与表情的非 接触心理压力检测 [J]. 光学学报,2021,41(3):68-77.
[4] 于路 . 基于心电指标的心理压力检测研究 [J]. 心理科学, 2017,40(2):277-282.
[5] 李永涛 . 基于心率变异性的心理压力连续检测 [D]. 重庆: 西南大学,2019.
[6] SHARMA,R,KHYATI C. EEG signal analysis and detection of stress using classification techniques [J].Journal of Information and Optimization Sciences, 2020,41(1):229-238.
[7] KALAS M S,MOMIN B F. Stress detection and reduction using EEG signals [C]//International Conference on Electrical, Electronics,and Optimization Techniques (ICEEOT).Chennai: IEEE,2016:471-475.
作者简介:林颖(1992—),男,汉族,广东揭阳人,专任教 师,硕士研究生,研究方向:模式识别。