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 Videos

Selection of electrode positions for an EEG-based brain computer interface (BCI)

M Pregenzer1, G Pfurtscheller, D Flotzinger

  • 1Ludwig-Boltzmann Institute of Medical Informatics and Neuroinformatic, Graz University of Technology.

Biomedizinische Technik. Biomedical Engineering
|October 1, 1994
PubMed
Summary

Selecting optimal electrode positions is crucial for Brain Computer Interfaces. This study used Distinction Sensitive Learning Vector Quantizer (DSLVQ) to identify key EEG electrode sites over sensorimotor areas for differentiating finger movements.

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

MRI-related anxiety can induce slow BOLD oscillations coupled with cardiac oscillations.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2021
Same author

Discussion of "time-frequency techniques in biomedical signal analysis: a tutorial review of similarities and differences".

Methods of information in medicine·2013
Same author

Toward a hybrid brain-computer interface based on imagined movement and visual attention.

Journal of neural engineering·2010
Same author

Discrimination of motor imagery-induced EEG patterns in patients with complete spinal cord injury.

Computational intelligence and neuroscience·2009
Same author

Could the beta rebound in the EEG be suitable to realize a "brain switch"?

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2008
Same author

Short-lived brain state after cued motor imagery in naive subjects.

The European journal of neuroscience·2008

Area of Science:

  • Neuroscience
  • Machine Learning
  • Biomedical Engineering

Background:

  • Designing effective Brain Computer Interfaces (BCIs) requires precise selection of electroencephalography (EEG) electrode positions.
  • Bypassing normal motor pathways necessitates understanding neural correlates of movement intention.
  • Existing methods for electrode selection may not optimally capture subtle differences in neural activity.

Purpose of the Study:

  • To investigate optimal electrode selection for EEG-based BCIs using a novel machine learning approach.
  • To identify specific EEG electrode locations that best differentiate between planning of left and right index finger movements.
  • To evaluate the efficacy of Distinction Sensitive Learning Vector Quantizer (DSLVQ) in feature selection for BCI applications.

Main Methods:

Related Experiment Videos

  • Utilized a Distinction Sensitive Learning Vector Quantizer (DSLVQ), an extension of Learning Vector Quantizer (LVQ) with a weighted distance function.
  • Analyzed 56-channel EEG recordings from three subjects during the preparation phase of discrete left or right index finger flexions.
  • Applied DSLVQ for dynamical scaling and feature selection to identify the most informative electrode positions.

Main Results:

  • DSLVQ identified specific electrode positions crucial for distinguishing between left and right index finger movement planning.
  • The most important electrode positions were found to be located over the cortical finger/hand areas in both brain hemispheres.
  • This suggests a somatotopic organization reflected in EEG signals during movement preparation.

Conclusions:

  • The study successfully demonstrated the utility of DSLVQ for optimizing electrode selection in EEG-based BCIs.
  • Key electrode positions over sensorimotor cortical areas are vital for accurate classification of motor intentions.
  • Findings contribute to the design of more efficient and effective BCIs for motor rehabilitation and control.