ECG Biometric Identification Using ST RT QT Distance Measures

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current biometric systems face challenges with high False Rejection Rates (FRR) and computational complexity, particularly in ECG-based identification methods that require multiple heartbeats and complex feature extraction, making them inefficient for real-time recognition in small-scale devices.

Innovation Solution

A method using ECG morphology-derived characteristics from three distance measures (ST, RT, and QT) between fiducial points, allowing identification with a single heartbeat through fast signal processing and machine learning techniques, with a normalization step to compensate for heart rate variability, enabling low computational cost and high accuracy recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If ECG-based biometric systems use multiple heartbeats and complex feature extraction, then identification accuracy improves, but computational complexity and processing time increase

Engineering Contradiction:
Improveidentification accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the most essential features from ECG signals - specifically three distance measures (ST, RT, QT) between fiducial points - rather than using complex feature extraction methods. This selective extraction of critical information maintains identification accuracy while dramatically reducing computational complexity and enabling implementation in small-scale devices

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the identification process to use only one or a few heartbeats rather than requiring multiple heartbeats. By focusing on extracting meaningful features from minimal cardiac cycles, the system reduces processing time and computational load while maintaining sufficient accuracy for reliable identification

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If ECG-based systems process multiple heartbeats, then recognition accuracy improves, but recognition time increases

Engineering Contradiction:
Improverecognition accuracyVSAvoidrecognition time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial action by processing only one or a few heartbeats instead of requiring multiple heartbeats for identification. This partial processing approach, combined with efficient feature extraction of three key distance measures, achieves near-perfect accuracy (99.48%) while reducing recognition time to approximately 0.75 to 3 seconds

Inventive Principle:
Principle #16Partial or excessive action

3Productivity

If traditional biometric methods are used, then identification can be performed, but False Rejection Rate increases

Engineering Contradiction:
Improveidentification efficiencyVSAvoidFalse Rejection Rate
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent changes the parameters used for ECG analysis by focusing on three specific distance measures (ST, RT, QT) between fiducial points rather than using traditional complex feature sets. This parameter transformation, combined with normalization to account for heart rate variability, achieves near-perfect accuracy (99.48%) and dramatically reduces the False Rejection Rate to approximately 0.52%

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3449409B1Biometric method and device for identifying a person through an electrocardiogram (ECG) waveform
Publication Date: 2021.07.28 INESC TEC INST DE ENGENHARIA DE SISTEMAS E COMPUTADORES TECHA E CIENCIA
  • EP3449409B1 patent drawingFigure 1~2
  • EP3449409B1 patent drawingFigure 3
  • EP3449409B1 patent drawingFigure 4~5

AI summary

Method for identifying a person through an electrocardiogram, ECG, waveform, said method comprising: capturing ECG signals from a sample population including the person to be identified; computing sample population ECG distances ST, RT and QT from the captured ECG signals; training a computer classification model on the computed sample population ECG distances, provided that no other ECG distances are used; capturing an ECG signal from the person to be identified; computing the person's ECG distances ST, RT and QT from the person's captured ECG signal; using the classification model with the person's computed ECG distances to identify the person to be identified within the sample population. Device for identifying a person through an electrocardiogram, ECG, waveform, said device comprising means for carrying out said method.