ECG Biometric Authentication Noise Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric authentication using electrocardiograms (ECGs) faces challenges due to signal variability and noise interference, making reliable identification and authentication difficult.
Innovation Solution
A system and method employing dynamic machine learning, specifically using support vector machines and neural networks, to improve the extraction of ECG features from detected signals, combined with a portable input device and capacitive touch sensors for enhanced signal detection and noise reduction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ECG signals are used for biometric authentication, then unique physiological features are captured, but signal variability and noise interference reduce identification reliability
Solution Approach 1:
The ECG signal processing is divided into multiple stages: raw signal acquisition, preprocessing (filtering and noise removal), feature extraction (identifying P-QRS-T complexes and intervals), and template comparison. This segmentation allows each stage to optimize for its specific function, improving overall reliability despite signal variability
Solution Approach 2:
A reference template serves as an intermediary between the variable ECG signal and the authentication decision. The system creates a reference template from multiple ECG recordings during enrollment, then compares subsequent signals against this stabilized reference. This intermediary absorbs the variability and noise, enabling reliable identification
2Adaptability or versatility
If dynamic biometric parameters like ECG are used, then authentication captures physiological state, but inherent variability at any given moment makes matching difficult
Solution Approach 1:
During the enrollment phase, the system performs preliminary actions by collecting multiple ECG recordings and creating a reference template before actual authentication is needed. This advance preparation establishes a stable baseline that accounts for natural physiological variations, making subsequent matching more reliable
Solution Approach 2:
The system transforms the raw ECG signal parameters into standardized features (such as R-R intervals, QRS duration, and morphological characteristics) that are less susceptible to momentary physiological variations. This parameter transformation maintains adaptability to physiological state while improving matching reliability
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 approach enhances the reliability and robustness of ECG-based biometric authentication by effectively filtering noise and stabilizing signal features, improving identification and authentication accuracy.
Implementation Method 1
capacitive touch sensors for enhanced signal detection
Data Source
AI summary
A method and device for using ECG signals for biometric authorization that includes a machine-learning based signal processing approach for significantly removing noise signals from ECG signals being used. The present invention further includes a probability-based additional approach for further enhancing the signal relative to signal segments falsely identified as an actual ECG signal.