Abstract
Non-invasive photoplethysmography (PPG) technology was developed to track heart rate during physical activity under free-living conditions. Automated analysis of PPG has made it useful in both clinical and non-clinical applications. Because of their generalization capabilities, deep learning methods can be a major direction in the search for a heart rate estimation solution based on signals from wearable devices. A novel multi-headed convolutional neural network model enriched with long short-term memory cells (MH Conv-LSTM DeepPPG) was proposed for the estimation of heart rate based on signals measured by a wrist-worn wearable device, such as PPG and acceleration signals. For the PPG-DaLiA dataset, the proposed solution improves the performance of previously proposed methods. An experimental approach was used to develop the final network architecture. The average mean absolute error (MAE) of the final solution was 6.28 bpm and Pearson’s correlation coefficient between the estimated and true heart rate values was 0.85.
Highlights
Current changes in human lifestyle have resulted in a lack of physical activity, which is one of the leading risk factors for non-communicable diseases and deaths [1]
Awareness of the positive aspects of physical activity, along with progress in the field of microcontrollers, has contributed to the development of many wearable devices that allow for continuous physical activity monitoring
This work aimed to propose a novel neural network architecture, multi-headed convolutional neural network model enriched with long short-term memory cells, for heart rate (HR) estimation treated as a regression task
Summary
Current changes in human lifestyle have resulted in a lack of physical activity, which is one of the leading risk factors for non-communicable diseases and deaths [1]. Awareness of the positive aspects of physical activity, along with progress in the field of microcontrollers, has contributed to the development of many wearable devices that allow for continuous physical activity monitoring. The periodicity of measured light corresponds to the cardiac rhythm, which is used for HR estimation [6]. This method has one major drawback: during intense physical activity, the PPG signal is very susceptible to interference [7]. Researchers usually solve the described problem through advanced PPG signal processing or by enriching the developed methods with accelerometer signals that directly inform about the movement aspects of the device [9]. Many new methods have been developed based on two IEEE Signal Processing Cup 2015 (ISPC) datasets [10]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
