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

CNOT9 affects hepatocellular carcinoma proliferation and cell cycle through the PTEN/AKT/p53 signaling pathway.

Human cell·2026
Same author

pH-Ultrasensitive Polyester Nanoprobe for High-Contrast Tumor Imaging with Superior Biocompatibility.

Polymer science & technology (Washington, D.C.)·2026
Same author

Monotone Peridynamic Neural Operator for Nonlinear Material Modeling with Conditionally Unique Solutions.

Computer methods in applied mechanics and engineering·2026
Same author

The outcome of digital technology in microvascular free flap reconstruction for ORNJ: a retrospective study.

Frontiers in bioengineering and biotechnology·2026
Same author

rRGD3<sup>mu</sup>, a Triple-RGD Recombinant Peptide, Suppresses Malignant Phenotypes in Nasopharyngeal Carcinoma-Associated Models Through the Modulation of ITGB1-Associated FAK/AKT Signaling.

International journal of molecular sciences·2026
Same author

Biodegradation of tetracycline by Penicillium reticulisporum Te01 under adsorption-metabolism synergy.

Bioprocess and biosystems engineering·2026

Related Experiment Video

Updated: Jun 24, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

941

A diagonal masking self-attention-based multi-scale network for motor imagery classification.

Kaijun Yang1, Jihong Wang1, Liantao Yang1

  • 1Power Systems Engineering Research Center, Ministry of Education, College of Big Data and Information Engineering, Guizhou University, Guiyang 550025, People's Republic of China.

Journal of Neural Engineering
|June 4, 2024
PubMed
Summary

This study introduces a new network, DMSA-MSNet, for improved electroencephalography-based motor imagery classification in brain-computer interfaces. The model effectively extracts features from EEG signals, enhancing classification accuracy.

Keywords:
convolutional neural networkfusionmotor imagerymulti-scaleself-attention

More Related Videos

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients
09:42

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

1.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Related Experiment Videos

Last Updated: Jun 24, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

941
Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients
09:42

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

1.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Computer Science

Background:

  • Electroencephalography (EEG)-based motor imagery (MI) is crucial for brain-computer interfaces (BCIs).
  • Challenges in EEG signal processing include non-stationarity and low signal-to-noise ratio, hindering high-precision MI classification.

Purpose of the Study:

  • To propose a novel Diagonal Masking Self-Attention-based Multi-Scale Network (DMSA-MSNet) for enhanced MI classification.
  • To effectively extract and emphasize features from EEG signals at different scales.

Main Methods:

  • A multi-scale temporal-spatial block was developed for local feature extraction across various receptive fields.
  • An adaptive branch fusion block was designed to integrate features from different scales.
  • A diagonal masking self-attention block was introduced for long-range global information analysis.

Main Results:

  • The DMSA-MSNet demonstrated superior performance compared to existing state-of-the-art models.
  • The model achieved high precision in MI classification on benchmark datasets (BCI Competition IV 2a and 2b).

Conclusions:

  • The DMSA-MSNet effectively extracts rich information from EEG signals.
  • This study provides a robust solution for improving motor imagery classification in BCI applications.