Estimating Heart Rate during Steady-State Activities and Transitions Based on Signal of PPG and ACC

Photoplethysmography (PPG) signal has often been used to non-invasively monitor heart rate (HR). However, it's difficult to obtain accurate HR during exercise because of motion artifacts (MA). Accelerometer (ACC) is a common wearable sensor, which can effectively reflect the users' body movement. In this paper, we present a method based on synchronized PPG and ACC to estimate HR during steady-state activities and related transitions. Firstly, we locate the steady state and transitional state by ACC signal. In steady-state activities, HR is obtained by spectrum peak screening. In the transitional-state activities, the spectrum search range is narrowed and then screen the peaks to estimate HR. The method was validated with the IEEE Signal Processing Cup 2015 challenge database. Pearson's correlation coefficient between PPG-estimated and true HR was 0.9933, and the mean absolute error (MAE) between them was 1.3262 beats per minute (BPM).