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: Jun 24, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

A New Dual-Attention Multi-Node Fusion Network for EEG-fNIRS Motor Imagery Classification.

Lufeng Feng, Baomin Xu, Li Duan

    IEEE Journal of Biomedical and Health Informatics
    |June 22, 2026
    PubMed
    Summary

    This study introduces a novel dual attention mechanism fusion network (DAMFNet) for improved brain-computer interface (BCI) performance using electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals. DAMFNet enhances motor imagery (MI) classification accuracy by effectively fusing multimodal data.

    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

    Immune-dominated cellular heterogeneity and stromal plasticity in keloid infiltrating and hypercellular zones revealed by single-cell RNA sequencing.

    Frontiers in immunology·2026
    Same author

    Vertexformer: the interpretable predictive research on thermocapillary convection of large Prandtl number liquid bridges.

    NPJ microgravity·2026
    Same author

    Hard Lewis Base-Driven Crystallization Control for Efficient All-Perovskite Tandem Solar Cells.

    Advanced materials (Deerfield Beach, Fla.)·2026
    Same author

    Efficacy of different exercise interventions on cognitive function in adults with major depressive disorder and subthreshold depression: a systematic review with pairwise and network meta-analyses.

    European archives of psychiatry and clinical neuroscience·2026
    Same author

    Intrinsic Manipulation of Interfacial Water in Titanium Carbide MXene via Carbon Vacancy Engineering for Superior Pseudocapacitive Storage.

    Small (Weinheim an der Bergstrasse, Germany)·2026
    Same author

    Anatomical location overrides biologically effective dose as a predictor of keloid recurrence after adjuvant radiotherapy: a systematic review and meta-regression.

    Strahlentherapie und Onkologie : Organ der Deutschen Rontgengesellschaft ... [et al]·2026

    Area of Science:

    • Neuroscience
    • Biomedical Engineering
    • Signal Processing

    Background:

    • Brain-computer interfaces (BCI) enable device control via neural signals.
    • Motor imagery (MI) decoding using electroencephalogram (EEG) faces challenges like low spatial resolution and noise.
    • Functional near-infrared spectroscopy (fNIRS) offers complementary data but its fusion with EEG requires further exploration of spatio-temporal features.

    Purpose of the Study:

    • To propose a novel multimodal EEG-fNIRS fusion model for enhanced MI classification and recognition.
    • To explore and exploit the spatio-temporal characteristics of combined EEG and fNIRS signals.
    • To develop a deep learning model that effectively fuses multimodal data while minimizing interference.

    Main Methods:

    • A dual attention mechanism fusion model (DAMFNet) was developed, featuring two feature extraction branches and a central fusion network.

    Related Experiment Videos

    Last Updated: Jun 24, 2026

    Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
    11:28

    Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

    Published on: June 30, 2018

  • Two fusion layers within the central network were designed to capture spatio-temporal features from both EEG and fNIRS.
  • Features were fused in the filter dimension to reduce redundancy, mine sensor correlations, and prevent adverse signal interactions.

    • Main Results:

    • DAMFNet demonstrated superior performance compared to STA-Net and M2NN on Dataset1, achieving improvements of 4.49% and 2.88%, respectively.
    • The proposed model exhibited competitive performance on Dataset2.
    • The fusion strategy effectively reduced mutual interference between EEG and fNIRS signals, enabling better cross-modal correlation learning.

    Conclusions:

    • The developed DAMFNet model effectively fuses multimodal EEG and fNIRS data for improved MI classification.
    • The dual attention mechanism and filter-dimension fusion strategy enhance the model's ability to learn cross-modal correlations.
    • This approach offers a promising direction for advancing BCI technology by leveraging complementary neuroimaging modalities.