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

Using time-dependent neural networks for EEG classification.

E Haselsteiner1, G Pfurtscheller

  • 1Department of Medical Informatics, Graz Technical University, Austria. hasi@dpmi.tu-graz.ac.at

IEEE Transactions on Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
|February 24, 2001
PubMed
Summary
This summary is machine-generated.

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
Same journal

Patient-driven control of FES-supported standing up and sitting down: experimental results.

IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2001
Same journal

The use of selective electrical stimulation of the quadriceps to improve standing function in paraplegia.

IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2001
Same journal

WARD: a pneumatic system for body weight relief in gait rehabilitation.

IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2001
Same journal

Electrotactile adaptation on the abdomen: preliminary results.

IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2001
Same journal

A navigation system for increasing the autonomy and the security of powered wheelchairs.

IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2001
Same journal

Determination of generic body-seat interface shapes by cluster analysis.

IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2001
See all related articles

Finite impulse response (FIR) multilayer perceptrons (MLPs) show superior performance in classifying electroencephalograph (EEG) data for brain-computer interfaces (BCI). This study highlights FIR MLPs as a more effective neural network topology for BCI applications compared to standard MLPs.

Area of Science:

  • Neuroscience
  • Computer Science
  • Signal Processing

Background:

  • Brain-computer interfaces (BCI) enable communication and control through neural signals.
  • Electroencephalograph (EEG) data is commonly used in BCI due to its non-invasiveness.
  • Classifying single-trial EEG data presents challenges in capturing temporal dynamics.

Purpose of the Study:

  • To compare the performance of standard Multilayer Perceptrons (MLPs) with Finite Impulse Response (FIR) MLPs for single-trial EEG classification.
  • To investigate the efficacy of incorporating FIR filters within MLPs for enhanced temporal processing in BCI.
  • To evaluate the practical application of these neural network topologies in a BCI experiment.

Main Methods:

  • Introduction to time series classification principles.

Related Experiment Videos

  • Description and theoretical comparison of standard MLPs and FIR MLPs.
  • Implementation and testing of both MLP architectures on single-trial EEG data from three BCI subjects.

    • Main Results:

    • FIR MLPs demonstrated higher classification accuracy compared to standard MLPs.
    • The temporal processing capability of FIR filters within MLPs proved beneficial for EEG data.
    • Consistent performance improvements were observed across different subjects.

    Conclusions:

    • FIR MLPs represent a more effective neural network architecture for single-trial EEG classification in BCI.
    • The integration of FIR filters enhances the ability of MLPs to process temporal information crucial for BCI.
    • This study provides evidence for the superiority of FIR MLPs in BCI applications.