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

Benchmarking ERP Analysis: Manual Features, Deep Learning, and Foundation Models.

Yihe Wang, Zhiqiao Kang, Bohan Chen

    IEEE Transactions on Bio-Medical Engineering
    |April 30, 2026
    PubMed
    Summary
    This summary is machine-generated.

    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

    WAFF: A Synergetic Face Forgery Video Detection Method via Weakly Supervised EfficientNet.

    Journal of imaging·2026
    Same author

    Plasma-activated nanocellulose for sustainable Pickering emulsions: Enhanced stability and antibacterial performance.

    Carbohydrate polymers·2026
    Same author

    A novel continuous-flow three-stage tandem system based on partial nitrification/Anammox granular sludge and partial denitrification-Anammox biofilm (PN/A-PD-A) for advanced nitrogen removal from mature landfill leachate.

    Bioresource technology·2026
    Same author

    Pathogenicity variation of CC4821 Neisseria meningitidis in China from 2005 to 2024.

    Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases·2026
    Same author

    Pathogenicity and vaccine protection of circulating pertactin- and filamentous hemagglutinin-deficient <i>Bordetella pertussis</i> strains.

    Emerging microbes & infections·2026
    Same author

    LLM-Based Pose Normalization and Multimodal Fusion for Facial Expression Recognition in Extreme Poses.

    Journal of imaging·2026
    Same journal

    SleepConFormer: A Single-Channel EEG Framework for Sleep Staging and Consciousness Assessment in Patients with Disorders of Consciousness.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    Modeling Partial and Total Support of Left Ventricular Assist Device for Discrete Hemodynamic Control Framework.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    A Low-Cost Wearable TI-TACS Stimulator With Bipolar Quadratic-Boost Converter for Current Stimulation Validation in the Rat Brain.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    EMG-Based Gait Estimation Using Koopman-Inspired Method.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    Soft Everting Robots for Medical Applications: A Review.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    Arterial spin labeling cerebral blood flow quantification from quantitative transport mapping based on multiscale fluid mechanics simulation and deep learning.

    IEEE transactions on bio-medical engineering·2026
    See all related articles

    This study benchmarks deep learning and traditional methods for analyzing event-related potentials (ERPs) from electroencephalography (EEG) data. Deep learning models show promise for ERP analysis, offering a framework for future research.

    Area of Science:

    • Neuroscience
    • Computational Neuroscience
    • Machine Learning

    Background:

    • Event-related potentials (ERPs) are crucial electroencephalography (EEG) measures reflecting cognitive processing and neurological states.
    • Current ERP analysis often relies on manual feature extraction, with deep learning applications underexplored.
    • Advances in deep learning for spontaneous EEG contrast with limited exploration in ERP analysis.

    Purpose of the Study:

    • To comprehensively benchmark traditional manual features, deep learning models, and pre-trained EEG foundation models for ERP analysis.
    • To evaluate the effectiveness of various token-embedding strategies in Transformer architectures for ERP data.
    • To provide a framework for selecting and designing models for future ERP studies.

    Main Methods:

    Related Experiment Videos

  • A unified data preprocessing and training pipeline was established for consistent evaluation.
  • Traditional manual features with linear classifiers were compared against deep learning and foundation models.
  • Approaches were evaluated on ERP stimulus classification and brain disease detection across 12 datasets.

    • Main Results:

    • Deep learning models demonstrate significant potential for ERP analysis, outperforming traditional methods in certain tasks.
    • Specific token-embedding strategies within Transformer architectures show improved suitability for ERP data.
    • The benchmark provides empirical evidence for the efficacy of different analytical approaches.

    Conclusions:

    • Deep learning and foundation models offer powerful alternatives to manual feature extraction in ERP analysis.
    • Tailoring embedding strategies within advanced architectures is key for optimizing ERP data processing.
    • This study establishes a foundational framework to guide future methodological choices in ERP research.