Morphological PPG Feature Extraction for Stress Estimation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing stress monitoring solutions using wearable devices rely heavily on heart rate variability (HRV) analysis, which is prone to errors due to precise detection of inter-beat intervals (IBIs) and is not effective in noisy environments or with low sampling rates.

Innovation Solution

The use of morphological photoplethysmography (PPG) features extracted from wearable devices, such as multimodal earbuds, combined with HRV features, to detect stress levels, employing a novel waveform quality check and artificial intelligence models for accurate stress estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If HRV analysis is used for stress monitoring, then stress detection capability is provided, but measurement precision deteriorates due to errors in IBI detection

Engineering Contradiction:

Improvestress detection accuracyVSAvoidIBI detection reliability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent transitions from using IBI-based HRV parameters to using morphological parameters of PPG waveforms (such as amplitude, width, area, and shape features). This parameter change allows stress detection to proceed without relying on precise IBI detection, thereby resolving the contradiction between stress detection capability and IBI detection reliability.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If PPG-based stress monitoring is implemented in wearable devices, then continuous monitoring capability is achieved, but measurement precision worsens due to noisy environments and low sampling rates

Engineering Contradiction:

Improvecontinuous monitoring capabilityVSAvoidstress detection precision

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies preliminary signal processing actions including noise filtering, waveform quality assessment, and morphological feature extraction before stress detection. These preliminary actions prepare the PPG signal to be robust against noisy environments and low sampling rates, enabling continuous monitoring while maintaining precision.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces traditional mechanical/electrical signal processing methods with morphological analysis of PPG waveforms. By focusing on the shape and structure of waveforms rather than temporal intervals, the system achieves noise resistance and maintains precision in resource-constrained wearable environments.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If morphological PPG features are used for stress detection, then measurement precision improves, but device complexity increases

Engineering Contradiction:

Improvestress detection accuracyVSAvoidsignal processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the PPG signal into individual waveforms and extracts morphological features from each waveform independently. This segmentation approach simplifies the overall processing by breaking down complex continuous signal analysis into manageable discrete waveform analyses, reducing device complexity while maintaining precision.

Inventive Principle:

Principle #1Segmentation

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

This approach improves the accuracy and precision of stress detection, even in noisy conditions and with low sampling rates, and provides continuous monitoring capabilities, comparable to electrocardiography (ECG) despite the smaller form factor of wearable devices.

Implementation Method 1

photoplethysmography (PPG) signal about a user

Methodology Applied

Scientific EffectPhotoplethysmography: Absorption (EM radiation)

Data Source

PatentUS20250082277A1Cardiac signal quality check and feature extraction pipeline using morphological features for stress level estimation

Publication Date: 2025.03.13 SAMSUNG ELECTRONICS CO LTD

AI summary

A computer-implemented method includes: receiving, from a sensor of an electronic device, a photoplethysmography (PPG) signal about a user; dividing the received PPG signal into a first set of waveforms; checking qualities of the first set of waveforms and generating a second set of waveforms based on the checked qualities of the first set of waveforms; extracting a plurality of morphological features of each waveform of the second set of waveforms and calculating a plurality of time/amplitude factors based on the extracted plurality of morphological features; estimating, using an artificial intelligence model, a stress level of the user, based on the calculated plurality of time/amplitude factors; and providing the estimated stress level to the user.