A sequential procedure for individual identity verification using ECG

Authors:
John M. Irvine;Steven A. Israel
Affiliations:
Advanced Signal Processing and Image Exploitation Group, Draper Laboratory, Cambridge, MA;Systems and Technology Division, SAIC, Arlington, VA
Venue:
EURASIP Journal on Advances in Signal Processing - Special issue on recent advances in biometric systems: a signal processing perspective
Year:
2009

Citing 11
Cited 3

A new adaptive scheme for ECG enhancement

Signal Processing
Improving visual evoked potential feature classification for person recognition using PCA and normalization

Pattern Recognition Letters
Advanced Methods And Tools for ECG Data Analysis

Advanced Methods And Tools for ECG Data Analysis
Verification of humans using the electrocardiogram

Pattern Recognition Letters
Classifier ensembles: Select real-world applications

Information Fusion
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Analysis of human electrocardiogram for biometric recognition

EURASIP Journal on Advances in Signal Processing
eigenPulse: Robust human identification from cardiovascular function

Pattern Recognition
Robust projective filtering of time-warped ECG beats

Computer Methods and Programs in Biomedicine
Invariant trajectory classification of dynamical systems with a case study on ECG

Pattern Recognition
ECG to identify individuals

Pattern Recognition

Laser Doppler vibrometry measures of physiological function: evaluation of biometric capabilities

IEEE Transactions on Information Forensics and Security
Biometric verification of a subject through eye movements

Computers in Biology and Medicine
Fiducial feature reduction analysis for electrocardiogram (ECG) based biometric recognition

Journal of Intelligent Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The electrocardiogram (ECG) is an emerging novel biometric for human identification. One challenge for the practical use of ECG as a biometric is minimizing the time needed to acquire user data. We present a methodology for identity verification that quantifies the minimum number of heartbeats required to authenticate an enrolled individual. The approach rests on the statistical theory of sequential procedures. The procedure extracts fiducial features from each heartbeat to compute the test statistics. Sampling of heartbeats continues until a decision is reached--either verifying that the acquired ECG matches the stored credentials of the individual or that the ECG clearly does not match the stored credentials for the declared identity. We present the mathematical formulation of the sequential procedure and illustrate the performance with measured data. The initial test was performed on a limited population, twenty-nine individuals. The sequential procedure arrives at the correct decision in fifteen heartbeats or fewer in all but one instance and in most cases the decision is reached with half as many heartbeats. Analysis of an additional 75 subjects measured under different conditions indicates similar performance. Issues of generalizing beyond the laboratory setting are discussed and several avenues for future investigation are identified.