Heart Rate Measurement Using Motion Artifact Elimination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wearable devices often fail to accurately measure heart rate during exercise due to motion artifacts, which can lead to inaccurate data and limited health monitoring capabilities.
Innovation Solution
A method involving the use of photoplethysmogram (PPG) data and motion data collected by wearable devices, where machine learning models differentiate between actual heart rate measurements and those attributed to motion, allowing for the selection of accurate heart rate data. This includes preprocessing and merging motion and PPG data to identify candidate heart rate measurements and eliminate artifacts, enabling continuous heart rate monitoring during various activities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If PPG data is collected during exercise, then heart rate monitoring capability is provided, but measurement accuracy deteriorates due to motion artifacts
Solution Approach 1:
The patent segments the heart rate measurement process into multiple candidate measurements, each potentially corresponding to different physiological events (e.g., actual heartbeats vs. motion artifacts). By dividing the continuous PPG signal into discrete candidate events and evaluating each independently, the system can distinguish true heart rate signals from motion-induced artifacts, thereby maintaining measurement accuracy during exercise.
Solution Approach 2:
The patent introduces motion data as an intermediary element that mediates between the PPG signal and the final heart rate determination. By comparing PPG-derived candidate heart rate measurements with concurrent motion data, the system can identify and eliminate measurements that correlate with motion artifacts, thus improving accuracy while maintaining exercise monitoring capability.
2Loss of information
If multiple candidate heart rate measurements are identified, then comprehensive heart rate data is obtained, but data processing complexity increases
Solution Approach 1:
The patent performs preliminary filtering and evaluation of candidate heart rate measurements using motion data before final selection. By pre-assessing each candidate measurement's likelihood of being an artifact based on motion correlation, the system reduces the computational burden of analyzing all candidates in detail, thus managing processing complexity while preserving data completeness.
Solution Approach 2:
The system uses the motion data itself to serve the dual purpose of both characterizing exercise activity and filtering heart rate candidates. The motion data automatically provides reference information that enables the system to self-evaluate and select valid heart rate measurements without requiring external validation or complex manual processing.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The solution provides comprehensive and accurate heart rate data, allowing users to track their health effectively during exercise and other activities, improving the reliability of wearable devices in monitoring physiological metrics.
Implementation Method 1
Some wearable devices may measure heart rate of a user by detecting changes in blood pulse volume through PPG sensors in the wearable device (e.g., infrared PPG sensors, infrared light emitting diodes (LEDs))
Data Source
AI summary
Methods, systems, and devices for heart rate detection are described. A method for measuring heart rate for a user may include receiving physiological data associated with the user, wherein the physiological data may include photoplethysmogram (PPG) data and motion data collected throughout a first time interval via a wearable device associated with the user. The method may include determining a set of candidate heart rate measurements within the first time interval based at least in part on the PPG data, selecting a first heart rate measurement from the set of candidate heart rate measurements based on the received motion data, and determining a first heart rate for the user within the first time interval based on the selected first heart rate measurement.