Heart rate estimation method for various fitness exercise states for wearable heart rate monitoring device and device thereof

Abstract

The invention discloses a heart rate estimation method for various fitness exercise states for a wearable heart rate monitoring device and a device thereof. The method includes sparse dictionary learning, motion state recognition, motion artifact removal and heart rate peak tracking; a pulse wave signal and a noise estimation signal in a certain motion state are used as a training set, and a sparse dictionary corresponding to the motion is obtained by solving the optimization problem of the sparse dictionary learning; then feature information from the motion signal is extracted and the motionstate recognition is performed based on a classification method, and the motion state corresponding to the pulse wave signal in the current time window is obtained; according to the motion state, whether the pulse wave signal contains a large amount of noise or not is determined, the sparse dictionary corresponding to the current motion state is selected, and sparse representation of the pulse wave signal is used to remove the noise interference to obtain a reconstructed pulse wave signal; and finally a heart rate peak of each time window is located. The heart rate estimation precision is high, and complexity is low.

Description

technical field [0001] The invention relates to the field of biomedical signal processing, in particular to a heart rate estimation method and device for wearable heart rate monitoring equipment. Background technique [0002] Heart rate monitoring based on modern wearable devices has attracted attention due to its effectiveness in controlling training load or fitness health monitoring. Heart rate monitoring based on photoplethysmography is popular because of its portability and low cost. However, heart rate monitoring based on photoplethysmography signals during exercise is a difficult challenge because photoplethysmography signals are susceptible to motion artifacts. [0003] In fitness exercises, photoplethysmography (PPG) signals are easily affected by motion artifacts, the main source of which is some voluntary or involuntary movements of the subject, which may cause a gap between the sensor of the hand and the skin during exercise. The gap between them expands. Motio...

AI Technical Summary

Problems solved by technology

However, since the performance of most existing schemes is only evaluated using some specific motions, such as walking and running

In practice, since there are many different types of sports, such as squats and elliptical machines, heart rate monitoring must be performed in many different types of exercise states, where hand movements have different directions, leading to more complex Motion artifacts make heart rate monitoring a big challenge

Images