The Features of ECG Affected by Mood Change during Imagining the Near Future and a Mental States Estimation Model using the Features

Abstract

The purpose of this study is to estimate mental states quantitatively using an ECG signals for preventing depression and anxiety. Then, we focus on mood change during imagining the near future. ECG signals are measured from participants during imagining the near future and participants evaluate mood change during that. Features of heart rate variability (HRV) are extracted from this ECG signals and mental states are defined in four levels by mood change. The mental states are estimated using support vector machine (SVM) with forward stepwise as feature selection. The estimation result shows f-measure 0.48 and features contributing to mental states. That indicates the effectiveness of focusing on mood change during imagining the near future and estimating mental states using ECG signals during that.