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

Automatic differentiation of multichannel EEG signals.

B O Peters1, G Pfurtscheller, H Flyvbjerg

  • 1John von Neumann Institute for Computing, Forschungszentrum Jülich, D-52425 Jülich, Germany.

IEEE Transactions on Bio-Medical Engineering
|March 10, 2001
PubMed
Summary

This study demonstrates accurate recognition of intended finger or foot movements using electroencephalograms (EEGs). A committee of artificial neural networks achieved high accuracy, even before movement initiation.

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

How to Measure Load-Dependent Kinetics of Individual Motor Molecules Without a Force-Clamp.

Methods in enzymology·2017
Same author

How to Measure Separations and Angles Between Intramolecular Fluorescent Markers.

Methods in enzymology·2016
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

Combining single-molecule optical trapping and small-angle x-ray scattering measurements to compute the persistence length of a protein ER/K alpha-helix.

Biophysical journal·2009

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Electroencephalograms (EEGs) offer a non-invasive method for brain-computer interfaces.
  • Accurate decoding of motor intentions from EEG signals remains a challenge.

Purpose of the Study:

  • To develop and evaluate a multichannel classification method for recognizing intended finger and foot movements from EEG data.
  • To assess the performance of artificial neural networks in decoding motor intentions.

Main Methods:

  • A committee of artificial neural networks was employed for multichannel EEG classification.
  • The method automatically identified relevant spatial regions on the scalp.
  • Classification accuracy was tested on previously unseen EEG trials.

Related Experiment Videos

Main Results:

  • High recognition rates (75%-98%) for intended movements were achieved across subjects.
  • Classification accuracy was optimal during movement execution but showed an early peak upon cueing.
  • Frequency filtering did not enhance recognition performance.

Conclusions:

  • A committee-based neural network approach effectively decodes motor intentions from EEG.
  • Early detection of movement intention is possible before physical execution.
  • This method shows promise for advanced brain-computer interfaces.