PPG Signal Validation Using Motion Artifact Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for continuous user validation during authenticated sessions using Photoplethysmogram (PPG) signals are hindered by high motion artifacts and computationally intensive machine learning models, which increase processing time and reduce accuracy due to reliance on synthetic data generation.
Innovation Solution
A method that preprocesses PPG signals from wearable devices to select segments with minimal motion artifacts, performs template matching using Euclidean distance similarity measures, and continuously validates users by updating reference segments based on validation criteria, thereby reducing computational intensity and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are used for user validation, then validation accuracy can be improved, but computational intensity and processing time increase
Solution Approach 1:
The patent extracts and removes motion artifacts from PPG signals before validation, eliminating the need for complex machine learning models. By preprocessing the signal to remove harmful components (motion artifacts), the system achieves accurate validation using simpler, less computationally intensive methods.
Solution Approach 2:
The patent performs preliminary preprocessing of PPG signals to eliminate motion artifacts before validation. This advance preparation of the data ensures that subsequent validation can be performed accurately without requiring intensive computational resources during the actual validation process.
2Measurement precision
If motion artifacts are eliminated from PPG signals, then validation accuracy is improved, but additional processing time is required
Solution Approach 1:
The patent replaces complex continuous motion artifact elimination with a simpler segmentation approach. Instead of continuously processing and filtering the entire PPG signal, the system divides it into segments and selects only those with minimal motion artifacts, significantly reducing processing time while maintaining accuracy.
Solution Approach 2:
The patent applies partial action by processing only selected PPG segments rather than the entire continuous signal. By identifying and processing only the segments with minimal motion artifacts, the system achieves accurate validation without the computational burden of processing all signal data.
3Quantity of substance
If synthetic data generation is used for training, then data availability is improved, but validation accuracy decreases
Solution Approach 1:
The patent enables the system to validate users using their own actual PPG data segments that have been preprocessed to remove motion artifacts. By using real user data rather than synthetic data, the system achieves higher validation accuracy while maintaining data availability through efficient segmentation and selection of usable segments.
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 effectively maintains secure authenticated sessions with low false-negative rates and minimal reauthentication requests, enhancing the reliability and efficiency of user validation without the need for extensive data filtering or complex computations.
Implementation Method 1
simultaneously receiving a PPG signal from a PPG sensor of a wearable device worn by the authenticated user
Implementation Method 2
synchronized accelerometer data received from an accelerometer sensor of the wearable device
Data Source
AI summary
Embodiments herein provide a method and system for continuously validating a user during an established authenticated session using Photoplethysmogram (PPG) and accelerometer data. State of the art approaches are mostly based on feature extraction and ML modelling for PPG based continuous session validation, while a template based approach in the art follows a complicated approach. The method disclosed herein utilizes less computation intensive template based approach to continuously validate the user across the session. The method comprises preprocessing a PPG data or PPG signal acquired from a wearable device worn by the user to identify segments of negligible motion. A first segment, after authentication using conventional authentication mechanism, serves as the initial reference. The chosen segments are then tested one by one with respect to the reference. If the templates in a segment match those of the reference, it is updated as the new reference, else a re-authentication is triggered.