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

Application of Generative Adversarial Networks to Improve COVID-19 Classification on Ultrasound Images.

Journal of imaging·2025
Same author

Correction: Barbosa et al. Production of rGO-Based Electrospinning Nanocomposites Incorporated in Recycled PET as an Alternative Dry Electrode. <i>Polymers</i> 2022, <i>14</i>, 4288.

Polymers·2025
Same author

Classification of non-small cell lung cancer by histologic subtype using deep learning in public and private data sets of computed tomography images.

Radiologia brasileira·2025
Same author

Prototype of a Multimodal and Multichannel Electro-Physiological and General-Purpose Signal Capture System: Evaluation in Sleep-Research-like Scenario.

Sensors (Basel, Switzerland)·2025
Same author

Conservative method for vertical electrooculogram attenuation based on local suppression of ongoing EEG artifact templates.

PloS one·2024
Same author

Reply to the letter regarding the article entitled: "Access to rehabilitation after stroke in Brazil (AReA study): multicenter study protocol".

Arquivos de neuro-psiquiatria·2023

Related Experiment Video

Updated: Jan 18, 2026

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

1.8K

Classification of Different Motor Imagery Tasks with the Same Limb Using Electroencephalographic Signals.

Eric Kauati-Saito1, André da Silva Pereira2, Ana Paula Fontana3

  • 1Laboratory of Medical Signal and Images Processing, Biomedical Engineering Program, Alberto Luiz Coimbra Institute for Graduate Studies and Research in Engineering (COPPE), Federal University of Rio de Janeiro (UFRJ), Rio de Janeiro 21941-901, Brazil.

Sensors (Basel, Switzerland)
|September 13, 2025
PubMed
Summary

Brain-computer interfaces (BCI) show promise for neurorehabilitation after stroke. This study found that standard EEG signal processing techniques effective for different limb motor imagery (MI) do not perform well for same-limb MI tasks, suggesting new methods are needed.

Keywords:
brain–computer interfaceclassificationelectroencephalographyfeature extraction

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

2.0K
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

1.3K

Related Experiment Videos

Last Updated: Jan 18, 2026

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

1.8K
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

2.0K
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

1.3K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Rehabilitation Science

Background:

  • Stroke frequently causes long-term motor deficits, necessitating advanced neurorehabilitation strategies.
  • Brain-computer interfaces (BCI) utilizing electroencephalographic (EEG) signals from motor imagery (MI) offer a promising avenue for motor recovery by promoting neuroplasticity.
  • Effective BCI control relies on optimizing sequential signal processing stages: recording, preprocessing, feature extraction/selection, and classification.

Purpose of the Study:

  • To identify optimal combinations of feature extraction techniques, time windows, frequency ranges, and classifiers for MI-EEG signal classification.
  • To evaluate the performance of these optimized BCI parameters on two distinct datasets: BCI Competition 2008 IV 2a (BCI-C) and a custom NeuroSCP dataset.
  • To investigate the efficacy of standard MI-EEG classification methods for differentiating movements of different limbs versus the same limb.

Main Methods:

  • Systematic search for optimal parameter combinations (feature extraction, time window, frequency range, classifier) for MI-EEG classification.
  • Evaluation using the BCI Competition 2008 IV 2a dataset (multi-limb MI) and the NeuroSCP dataset (same-limb MI).
  • Comparative analysis of classification accuracy between datasets to assess the impact of limb specificity on BCI performance.

Main Results:

  • The BCI-C dataset (different limbs) achieved a mean classification accuracy of 76%, with individual accuracies ranging from 54% to 94%.
  • The NeuroSCP dataset (same limb) yielded a lower average classification accuracy of 53%, with individual results varying from 35% to 71%.
  • Performance disparities highlight that techniques successful for multi-limb MI classification are suboptimal for same-limb MI tasks.

Conclusions:

  • Standard EEG feature extraction and classification methods are less effective for distinguishing motor imagery of the same limb compared to different limbs.
  • The findings suggest a need for novel feature extraction approaches, such as EEG functional connectivity, for improved same-limb MI classification.
  • Future research should explore advanced techniques to enhance BCI performance in neurorehabilitation for patients with specific, same-limb motor impairments.