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

A Fast Approximate Method for Predicting the Behavior of Auditory Nerve Fibers and the Evoked Compound Action Potential (ECAP) Signal.

Journal of medical signals and sensors·2021
Same author

Low-Complexity Discriminative Feature Selection From EEG Before and After Short-Term Memory Task.

Clinical EEG and neuroscience·2016
Same author

Parametric study of irreversible electroporation with different needle electrodes: electrical and thermal analysis.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·2014
Same author

The effects of pulsed magnetic field exposure on the permeability of leukemia cancer cells.

Electromagnetic biology and medicine·2013
Same author

Local exposure of brain central areas to a pulsed ELF magnetic field for a purposeful change in EEG.

Clinical EEG and neuroscience·2013
Same author

Magnetic fields with frequency of 217 Hz can reduce cell apoptosis caused by electrochemotherapy.

Electromagnetic biology and medicine·2013

Related Experiment Video

Updated: Nov 29, 2025

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

1.8K

An EEG channel selection method for motor imagery based brain-computer interface and neurofeedback using Granger

Hesam Varsehi1, S Mohammad P Firoozabadi2

  • 1Department of Biomedical Engineering, Tarbiat Modares University, Tehran, Iran.

Neural Networks : the Official Journal of the International Neural Network Society
|November 21, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces a novel Granger causality (GC) method for electroencephalogram (EEG) channel selection in motor imagery (MI) brain-computer interfaces (BCI). The approach enhances BCI performance by reducing channels while improving classification accuracy.

Keywords:
Brain–computer interface (BCI)EEG channel selectionElectroencephalogram (EEG)Granger causalityMotor imagery (MI)Neurofeedback

More Related Videos

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
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

1.2K

Related Experiment Videos

Last Updated: Nov 29, 2025

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

1.8K
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
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

1.2K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Motor imagery (MI) brain-computer interfaces (BCI) and neurofeedback (NF) utilize electroencephalogram (EEG) signals for motor function enhancement and neurological restoration.
  • Effective BCI and NF implementations often require channel selection to reduce noisy and redundant EEG data.
  • Existing channel selection methods may not fully leverage the underlying causal interactions within EEG signals during MI tasks.

Purpose of the Study:

  • To propose a novel EEG channel selection method based on Granger causality (GC) analysis for improved MI-BCI and NF performance.
  • To investigate the effectiveness of causal interactions in reducing EEG channels while maintaining or enhancing classification accuracy.
  • To integrate machine learning for artifact detection and optimize feature extraction and classification for MI tasks.

Main Methods:

  • A novel channel selection method employing Granger causality (GC) analysis to identify causally interacting EEG channels.
  • Machine learning-based clustering of Independent Component Analysis (ICA) components to differentiate between artifact and normal EEG signals.
  • Feature extraction using Common Spatial Pattern (CSP) and regularized CSP (RCSP) followed by classification with k-NN, SVM, and LDA.

Main Results:

  • The proposed GC-based channel selection method achieved high classification performance with only eight selected EEG channels.
  • The method resulted in 93.03% accuracy, 92.93% sensitivity, and 93.12% specificity on the Physionet MI dataset.
  • Performance metrics showed significant improvements (3.95-4.13%) compared to a correlation-based channel selection method.

Conclusions:

  • Granger causality analysis offers an effective approach for EEG channel selection in MI-BCI and NF applications.
  • Causal constraint-based channel selection can lead to a reduced number of channels with superior classification performance.
  • The developed method provides a promising strategy for optimizing BCI and NF systems.