Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

ECG biometric using multilayer perceptron and radial basis function neural networks.

Vu Mai, Ibrahim Khalil, Christopher Meli

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |January 19, 2012
    PubMed
    Summary

    This study introduces a novel method for person identification using electrocardiogram (ECG) QRS complexes. Achieved over 98% accuracy with Multilayer Perceptron (MLP) neural networks, demonstrating ECG

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Effectiveness of vericiguat in heart failure across ejection fraction phenotypes: a comprehensive meta-analytic trial sequential analysis and meta-regression analysis.

    Annals of medicine and surgery (2012)·2026
    Same author

    Efficacy of Mavacamten on functional capacity in hypertrophic cardiomyopathy: a meta-analysis, meta-regression, and trial sequential analysis of randomized controlled trials.

    Annals of medicine and surgery (2012)·2026
    Same author

    Suicide and suicidal ideation among U.S. surgeons: A systematic review and meta-analysis of prevalence, risk groups, and temporal trends.

    American journal of surgery·2026
    Same author

    Efficacy and Safety of the Dual Glucagon-Like Peptide-1 and Glucagon Receptor Agonist Mazdutide in Predominantly Chinese Adults With Obesity and/or Type 2 Diabetes: A Systematic Review and Meta-Analysis.

    Diabetes, obesity & metabolism·2026
    Same author

    Co-occurrence of Griscelli Syndrome Type 2 and Systemic Juvenile Idiopathic Arthritis in a Pediatric Patient: A Case Report.

    Journal of investigative medicine high impact case reports·2026
    Same author

    Efficacy of tirzepatide versus SGLT2 inhibitors in metabolic dysfunction-associated steatotic liver disease (MASLD): a multicenter propensity-matched real-world study.

    Hepatology international·2026

    Area of Science:

    • Biometrics
    • Cardiovascular Signal Processing
    • Machine Learning

    Background:

    • Electrocardiogram (ECG) signals offer unique biometric features.
    • The QRS complex in ECG is stable against heart rate variability.
    • ECG-based biometrics is a growing field for identification.

    Purpose of the Study:

    • To propose and evaluate a new method for person identification using ECG QRS complexes.
    • To assess the efficacy of neural network models for QRS complex classification.
    • To determine the accuracy of ECG-based biometrics for individual identification.

    Main Methods:

    • Extraction of 324 QRS complexes from the Physionet MIT-BIH Normal Sinus Rhythm Database (NSRDB).
    • Utilized Multilayer Perceptron (MLP) and Radial Basis Function (RBF) neural networks for classification.

    Related Experiment Videos

  • Trained neural networks with carefully selected QRS complex data to cover a wide range of values.

    • Main Results:

    • Classification accuracy rates exceeding 98% were achieved using MLP.
    • Classification accuracy rates reaching 97% were achieved using RBF.
    • Demonstrated high accuracy in distinguishing individuals based on their QRS complex patterns.

    Conclusions:

    • ECG QRS complexes are a viable and accurate biometric feature for person identification.
    • MLP and RBF neural networks provide effective classification of QRS complexes for biometric purposes.
    • The proposed method shows significant potential for secure and non-invasive identification systems.