Personal optimization method to estimate mood using heart rate variability in daily life: Mood estimation using heart rate variability

Abstract

The aim of this study is to present a method of assessing eight types of mood 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 period during daily life. Eight types of mood are happiness, tension, fatigue, anxiety, depression, anger, vigor, and confusion. HRV and body accelerations were recorded from nine normal subjects for two months of normal daily life. Fourteen HRV indices were calculated with the HRV data at 512 seconds prior to the time of every mood level report. Data to be analyzed were limited to those with body accelerations of 30 mG (0.294 m/s2) and lower. Further, the differences from the reference values in the same time zone were calculated with both the mood score (Δmood) and HRV index values (ΔHRVI). The multiple linear regression model that estimates Δmood from the scores for principal components of ΔHRVI were then constructed for each individual. The data were divided into training data set and test data set in accordance with the 2-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 model was most effective on estimating tension compared with other seven types of mood. The subjects' mean Pearson correlation coefficient was 0.52 with the training data set and 0.40 with the test data set. We proposed a method of assessing mood that is optimized to every individual based on HRV data measured over a long period of daily life.