Wearable HRV Stress Measurement Under Motion Artifacts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wearable devices are unable to accurately calculate stress levels due to motion artifacts from insufficient skin contact, leading to inaccuracies in heart rate variability (HRV) measurements.
Innovation Solution
A wearable device calculates acute stress levels by comparing current daytime HRV to a user's baseline HRV, using a machine learning model to fill in missing or inaccurate data, and determines stress thresholds to classify stress states. It also evaluates cumulative stress over extended periods by comparing daytime and nighttime HRV data, and assesses resilience to stress through a resilience score based on aggregate stress indices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of moving object
If conventional wearable devices collect HRV data during motion, then continuous stress monitoring is enabled, but motion artifacts from insufficient skin contact cause measurement inaccuracies
Solution Approach 1:
The system performs preliminary actions by detecting motion states before HRV measurement and selecting appropriate measurement modes. When motion is detected, the system switches to motion-based stress estimation using accelerometer data, preventing motion artifacts from corrupting the HRV measurements. This preliminary detection and mode switching ensures continuous monitoring capability while maintaining measurement accuracy across different activity states.
Solution Approach 2:
The system changes measurement parameters based on motion state. During stationary periods, it uses traditional PPG-based HRV measurement with standard parameters. During motion, it transitions to motion-based estimation using accelerometer data with different computational parameters. This dynamic parameter adjustment resolves the contradiction by adapting the measurement approach to match the physical state, enabling continuous monitoring without sacrificing accuracy.
2Measurement precision
If multiple physiological parameters are collected to improve stress measurement accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The system implements multi-functionality by using a single wearable device to perform multiple functions: PPG-based HRV measurement, accelerometer-based motion detection, skin contact quality assessment, and context-aware stress estimation. Rather than requiring separate dedicated devices for each measurement type, this universal approach combines multiple capabilities in one system, improving stress measurement accuracy through data fusion while managing device complexity through integrated design.
Solution Approach 2:
The system uses motion data from the accelerometer as an intermediary to bridge the gap between PPG signal quality and stress measurement. When skin contact is insufficient or motion is detected, the accelerometer data serves as an intermediary parameter to estimate stress levels, compensating for the limitations of direct PPG-based HRV measurement. This intermediary approach improves accuracy without requiring additional specialized sensors.
3Duration of action of moving object
If motion-based stress estimation is used during activity, then continuous monitoring capability is maintained, but measurement precision during motion deteriorates due to artifacts
Solution Approach 1:
The system applies dynamics by continuously adapting the measurement methodology based on real-time motion state detection. Rather than using a static measurement approach, the system dynamically switches between PPG-based HRV measurement during stationary periods and motion-based estimation during activity. This dynamic adaptation maintains monitoring continuity across all activity states while optimizing measurement precision for each specific condition, resolving the contradiction between continuous monitoring and motion-era accuracy.
Data Source
AI summary
Methods, systems, and devices for measuring cumulative stress of a user are described. A system may determine a first and second baseline heart rate variability (HRV) values of the user during periods that the user is awake and asleep, respectively. The system may then acquire physiological data from the user throughout a time interval, and determine a first set of HRV values during periods that the user is awake, and a second set of HRV values during periods that the user is asleep. The system may then determine a cumulative stress level of the user based on comparisons between the first set of HRV values and the first baseline HRV value, and between the second set of HRV values and the second baseline HRV value, where the cumulative stress level is associated with a total amount and/or trend of the user's stress level experienced throughout the time interval.