Personal adaptive method to assess mental stress during daily life using long-term recorded physiological signals

本研究的目的是提出一种基于心率变异性（HRV）数据的心理紧张评估方法，该方法针对每个人进行了优化，以消除个体间变异性的影响，该数据是在日常生活中长时间（两个月）测量的。然后在消除身体运动和昼夜节律的影响后，为每个个体构建了从心率变异性指数主成分得分估计张力的多元线性回归模型。按照5重交叉验证法将数据分为训练数据集和测试数据集。利用训练数据集确定多元线性回归系数，并利用测试数据集检验优化模型的泛化能力。训练数据集的受试者平均值r=0.51，测试数据集的受试者平均值r=0.42。

The aim of this study is to present a method of assessing psychological tension that is optimized to every individual on the basis of the heart rate variability (HRV) data which, to eliminate the influence of the inter-individual variability, are measured in a long time (two months) period during daily life. The multiple linear regression model that estimates tension from the scores for principal components of heart rate variability indices were then constructed for each individual after eliminating the effects of body movement and circadian rhythm. The data were divided into training data set and test data set in accordance with the 5-fold cross validation method. Multiple linear regression coefficients were determined using the training data set, and with the optimized model its generalization capability was checked using the test data set. The subjects mean was r=0.51 with the training data set and r=0.42 with the test data set.