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 Video

Updated: May 14, 2026

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

MPAN: A Multi-Prototype Adaptive Network for Few-Shot EEG-Based Biometric Recognition.

Jing Tang, Honggang Liu, Xuanyu Jin

    IEEE Journal of Biomedical and Health Informatics
    |May 12, 2026
    PubMed
    Summary

    This study introduces a novel Multi-Prototype Adaptive Network (MPAN) for efficient electroencephalography (EEG) biometric recognition. The MPAN framework enables rapid adaptation to new users with limited data, improving scalability and generalization.

    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

    Developing and validating the English Classroom Teaching Enjoyment Scale for Chinese senior high school teachers.

    Acta psychologica·2026
    Same author

    Suppressing Gate-Induced Drain Leakage with an Asymmetric Gate Design in HiPco CNT FETs.

    Nanomaterials (Basel, Switzerland)·2026
    Same author

    Simulation and prediction of human brucellosis epidemic trends in Changji city.

    Infectious Disease Modelling·2026
    Same author

    LncRNA MIR4435-2HG-mediated succinylation of USF1 promotes its protein stability and induces epithelial-mesenchymal transition in HNSCC.

    Epigenetics·2026
    Same author

    The complex interplay between students' perceived teacher support, self-esteem, and demotivation in English learning.

    Acta psychologica·2026
    Same author

    A Self-Assembled Nanobody Against the Haemagglutinin of Influenza a Virus Shows Enhanced Stability and Efficacy <i>In Vitro</i> and <i>In Vivo</i>.

    Frontiers in bioscience (Landmark edition)·2026

    Area of Science:

    • Neuroscience
    • Biometrics
    • Machine Learning

    Background:

    • Electroencephalography (EEG) offers promising biometric recognition by capturing neural dynamics.
    • Current deep learning methods often require extensive subject-specific data or retraining, limiting scalability.

    Purpose of the Study:

    • To develop a novel framework for few-shot EEG-based biometric recognition that addresses scalability and generalization limitations.
    • To enable rapid adaptation to new subjects with minimal labeled data.

    Main Methods:

    • Proposed the Multi-Prototype Adaptive Network (MPAN), a dual-branch framework for few-shot EEG recognition.
    • Employed a Dual-Path Pretraining Network (DPPN) for learning robust EEG representations using supervised contrastive and mutual distillation losses.
    • Integrated complementary metric information via a multi-prototype fusion module for few-shot decision-making.

    Related Experiment Videos

    Last Updated: May 14, 2026

    Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
    11:25

    Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

    Published on: July 26, 2013

    Main Results:

    • MPAN achieved state-of-the-art performance on two public EEG benchmarks.
    • Demonstrated identification accuracies of 91.86% and 94.37% in a 16-way 5-shot setting.
    • Consistently surpassed existing baselines in few-shot recognition scenarios.

    Conclusions:

    • MPAN offers a practical solution for efficient new-subject enrollment in EEG biometrics, especially with limited data.
    • The framework shows significant potential for improving the generalization and scalability of EEG-based recognition systems.