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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Global Snow-free Leaf Area Index Dataset 1985-2020 for Earth System Modeling.

Scientific data·2026
Same author

Pestivirus bovine viral diarrhea virus infection induces ROS-HIF-1a axis-driven glycolytic reprogramming, which increases viral replication by impairing RIG-I-dependent type I interferon response.

Journal of virology·2026
Same author

Intense pulsed light rejuvenates UVB-induced photoaging in human keratinocytes and guinea pig skin by inhibition of ERK-AP-1-MMP pathway.

Scientific reports·2026
Same author

Maternal essential and toxic metal mixtures in late pregnancy and neonatal birth weight.

Environment international·2026
Same author

<i>Lactobacillus rhamnosus</i> confers protection against enteropathogenic bacteria by enhancing mucosal immunity and epithelial barrier function.

Frontiers in cellular and infection microbiology·2026
Same author

Dietary supplementation with chicken-derived L. rhamnosus CIQ249 protects broilers against enteropathogens by regulating intestinal homeostasis.

Letters in applied microbiology·2026

Related Experiment Video

Updated: Nov 30, 2025

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.5K

Convolutional Correlation Analysis for Enhancing the Performance of SSVEP-Based Brain-Computer Interface.

Yao Li, Jiayi Xiang, Thenkurussi Kesavadas

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |November 17, 2020
    PubMed
    Summary

    A new non-linear model, convolutional correlation analysis (Conv-CA), improves steady-state visual evoked potential (SSVEP) recognition for brain-computer interfaces (BCIs). Conv-CA significantly outperforms linear methods by using convolutional neural networks (CNNs) for non-linear EEG signal transformation and analysis.

    More Related Videos

    A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
    06:34

    A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

    Published on: July 7, 2023

    2.9K
    Assessment and Communication for People with Disorders of Consciousness
    07:37

    Assessment and Communication for People with Disorders of Consciousness

    Published on: August 1, 2017

    9.4K

    Related Experiment Videos

    Last Updated: Nov 30, 2025

    SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
    11:01

    SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

    Published on: November 24, 2015

    13.5K
    A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
    06:34

    A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

    Published on: July 7, 2023

    2.9K
    Assessment and Communication for People with Disorders of Consciousness
    07:37

    Assessment and Communication for People with Disorders of Consciousness

    Published on: August 1, 2017

    9.4K

    Area of Science:

    • Neuroscience
    • Biomedical Engineering
    • Machine Learning

    Background:

    • Current high-performance models for steady-state visual evoked potential (SSVEP) frequency recognition primarily rely on linear methods.
    • Electroencephalogram (EEG) signals from different channels exhibit non-linear relationships, limiting the accuracy of linear combinations for SSVEP classification.
    • Improving the performance of SSVEP-based brain-computer interfaces (BCIs) necessitates exploring non-linear approaches.

    Purpose of the Study:

    • To propose and evaluate a novel non-linear model, convolutional correlation analysis (Conv-CA), for enhanced SSVEP recognition.
    • To compare the performance of Conv-CA against established linear methods, specifically task-related component analysis (TRCA).
    • To investigate the explainability and potential for further optimization of the Conv-CA model.

    Main Methods:

    • Development of Conv-CA, a hybrid model combining convolutional neural networks (CNNs) with a self-defined correlation layer.
    • CNNs transform multi-channel EEG data into a single signal, capturing non-linear inter-channel and temporal dynamics.
    • The correlation layer computes coefficients between the transformed signal and reference signals, constraining the model's fitting space.

    Main Results:

    • Conv-CA significantly outperformed TRCA-based methods on a 40-class SSVEP benchmark dataset from 35 subjects.
    • The proposed non-linear model demonstrated superior accuracy in SSVEP classification compared to linear approaches.
    • Conv-CA offers good explainability through the analysis of its correlation layer inputs, aiding in understanding learned features.

    Conclusions:

    • Conv-CA represents a significant advancement in SSVEP recognition, offering a powerful non-linear alternative to existing linear methods.
    • The model's non-linear extension of spatial filters and its hybrid deep learning structure hold promise for future BCI development.
    • The approach of integrating neural networks with unsupervised features shows potential for broader applications in signal classification.