Heart rate trend forecasting during high-intensity interval training using consumer wearable devices

High-Intensity Interval Training is one of the most popular and dynamically developing fitness innovations in recent years. Professional runners have used interval training for a long time, alternating between high intensity sprints and low intensity jogging intervals to improve their overall performance. During such exercises, the accurate monitoring and prediction of heart rate dynamics is of particular importance to control the physiological state of a person and prevent possible pathological consequences. At the same time, heart rate estimation using very popular nowadays wearable devices (like smartwatches, fitness belts, etc.) during high-intensity exercises can be quite inaccurate. This inaccuracy mostly happens since the heart rate sensors (photoplethysmogram (PPG) and electrocardiogram (ECG)) are exposed to noises due to motion artifacts. PPG sensor suffers from periodic ambient light saturation due to intensive hand motions. ECG is noisy due to electrode contact area changes by body deformation. To solve the mentioned problem, in the current paper a deep learning framework for motion resistive heart rate estimation is developed. The system combines signal processing approaches for the raw sensor data processing and a deep learning architectures (convolutional and recurrent neural networks) for a real-time heart rate measurements and forecasting future heart rate dynamics.