Wearable Stress Sensing With Underside cEDA Electrodes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wearable biometric monitoring devices face challenges in accurately measuring continuous electrodermal activity (cEDA) for detecting acute stress events due to the need for continuous skin contact, which is not feasible with electrodes mounted on the top face, limiting the effectiveness of stress detection and monitoring.
Innovation Solution
A wearable computing device with biometric sensor electrodes on the underside for continuous skin contact, combined with a Momentary Stress Algorithm (MSA) that processes time-series data from multiple sensors, applies filtering techniques, and selects models to calculate stress indicators, triggering notifications or functions when thresholds are exceeded.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If electrodes are mounted on the top face of the device, then the device structure is simpler, but continuous skin contact cannot be maintained for accurate cEDA measurement
Solution Approach 1:
The patent inverts the conventional electrode placement by positioning cEDA electrodes on the underside of the wearable device rather than the top face. This inversion enables continuous skin contact during normal wear, allowing accurate cEDA measurements without requiring user intervention to maintain contact.
2Duration of action of stationary object
If electrodes are positioned on the underside for continuous skin contact, then continuous cEDA measurement is enabled, but the device requires more careful design and positioning
Solution Approach 1:
The patent implements continuous cEDA measurement by positioning electrodes on the underside of the device, enabling uninterrupted skin contact during normal wear. This continuous configuration allows the device to maintain measurement functionality over extended periods without requiring user intervention or frequent repositioning.
3Measurement precision
If multiple sensors and filtering techniques are applied, then stress detection accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent segments the stress detection process into distinct stages: collecting data from multiple sensors (cEDA, heart rate, temperature, accelerometer), processing each sensor type through specific filtering techniques, and then integrating the processed data to detect stress events. This segmentation allows complex processing to be managed systematically.
Solution Approach 2:
The patent applies filtering techniques to sensor data in advance before stress event detection. By pre-processing the data to remove artifacts and noise, the system prepares clean data for accurate stress detection, reducing the computational burden during the actual detection phase.
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 device provides accurate and continuous stress detection, enabling users to be aware of acute stress events and offering countermeasures, enhancing stress awareness and management.
Implementation Method 1
skin conductance is calculated using the measured electrical impedance
Implementation Method 2
input of other sensors (e.g., photoplethysmography data (such as amplitude))
Data Source
AI summary
A method of monitoring stress of a user includes receiving a plurality of time-series data inputs from a plurality of biometric sensor electrodes of a wearable computing device. The time-series data inputs includes continuous electrodermal activity data and at least one of heart rate data, skin temperature data, and heart rate variability data. The method also includes processing the time-series data inputs using a plurality of filtering techniques in sequence. Further, the method includes selecting a model from a plurality of models based on types of data inputs received as the time-series data inputs to calculate an indicator of a physiological response of the user at a certain time. Thus, the selected model is tailored to use all of the time-series data inputs in the calculation of the indicator of the physiological response. Further, the method includes controlling a function of the device when the indicator of the physiological response exceeds a threshold.