A Stress Analysis Method using Poincaré Plot and Complex Correlation Measures for Wearable Health Devices
Abstract: This paper attempts to develop a stress analysis method using short-term heart rate (HR) data obtained with wearable health devices. Evaluation method for stress analysis is very important for disease prevention and health promotion. Wearable health devices, such as smart phones and wristband fitness watches, are capable of measuring HR data using photoplethysmography technologies. In recent years, many new commodity devices have been issued and been used to obtain healthcare information, including HR data, in people’s everyday life. However, since HR data of wearable devices are recorded with uneven and relatively long sampling intervals, which are constrained by their hardware issues, it is difficult to apply traditional spectral analysis methods for the HR data. The proposed method evaluates HR data using a non-linear technique, Poincaré plot. As the number of points in a plot is restricted by the limited sampling features of wearable devices, this paper applies two stress analysis indices that are based on complex correlation measures of time-varying characteristics in Poincaré plots. On the other hand, the proposed method can investigate dynamic changes in stress levels of short-term (e.g., one minute) analysis duration. Mental stress induction experiments were conducted with nine subjects to validate the proposed method.
Keywords: Stress analysis; Wearable health devices; Heart rate variability (HRV); Poincaré plot; Complex correlation measure (CCM)