PPG Motion Artifact Reduction via ICA Decomposition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Photoplethysmography (PPG) data is susceptible to motion-induced signal distortions, leading to erroneous interpretation and reduced accuracy in cardiovascular parameter estimation, limiting its application in real-world environments due to the dominance of motion artifacts over vital signals.
Innovation Solution
A data processing device and method that decompose sensor data indicative of position, velocity, or acceleration into motion reference data channels, allowing for the removal of motion artifacts from PPG data without relying on previous sensor data history, enabling real-time processing and improved accuracy in extracting vital signals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If PPG technique is used to acquire cardiovascular information unobtrusively, then ease of operation and adaptability are improved, but motion artifacts dominate the signal causing reduced measurement precision and reliability
Solution Approach 1:
The PPG signal is decomposed into multiple independent components using Independent Component Analysis (ICA), separating the vital signal from motion artifacts. Each component represents a distinct source, allowing selective processing to remove artifact-dominated components while preserving the physiological signal.
Solution Approach 2:
An intermediary processing stage is introduced between signal acquisition and final analysis. This stage applies ICA decomposition and component selection algorithms to act as a mediator that filters out motion artifacts while preserving the vital signal, enabling accurate measurement even during motion.
2Measurement precision
If subjects are required to remain motionless to reduce motion artifacts, then measurement precision is improved, but ease of operation and adaptability to real-world environments deteriorate
Solution Approach 1:
The motion artifacts, which were previously harmful and required motionless conditions, are converted into useful information. By decomposing the signal into independent components, the method identifies and utilizes components dominated by motion to create motion reference data, which is then used to remove artifacts from the vital signal, enabling accurate measurement during natural motion.
3Measurement precision
If motion artifacts are removed using traditional methods requiring previous sensor data history, then measurement precision may be improved, but processing speed and productivity deteriorate due to inability to process in real-time
Solution Approach 1:
Motion reference data channels are pre-computed from the PPG signal components before the artifact removal process. This preliminary decomposition and identification of motion-dominated components enables the subsequent artifact removal to proceed efficiently in real-time without requiring extensive historical data, as the motion characteristics are already characterized in separate channels.
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 effectively reduces motion artifacts in PPG data, enhancing the accuracy and reliability of cardiovascular parameter estimation, making PPG technology more suitable for use in medical and everyday life settings, including sports environments.
Implementation Method 1
A signal (e.g., physiological signal) comprising at least two signal channels is decomposed using independent component analysis (ICA) into at least two independent components
Implementation Method 2
a de-noised version of the signal is generated by preserving in the signal only one or more independent components of the at least two independent components belonging to the signal space
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
Motion artifact reduction using multi-channel PPG signals A data processing device (100, 200) is disclosed for extracting a desired vital signalcontaining a physiological information component from sensor data that includes time- dependent first sensor data (PPG1) comprising the physiological information component and at least one motion artifact component, and that includes time-dependent second sensor data that is indicative of a position, a velocity or an acceleration of the sensed region as a function of time. A decomposition unit (104, 204) decomposesthe second sensor data into at least two components of decomposed sensor data and, based on the decomposed second sensor data, provides at least two different sets of motion reference data in at least two differentmotion reference data channels. An artifact removal unit (106, 206) determinesthe vital signal formed from a linear combination of the first sensor data and the motion reference data of at least one two of the motion reference data channels.