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

Adaptive proximity to criticality underlies amplification of ultra-slow fluctuations during free recall.

PLoS computational biology·2025
Same author

The Hypno-PC: uncovering sleep dynamics through principal component analysis and hidden Markov modeling of electrophysiological signals.

Sleep·2025
Same author

The Posterior Dominant Rhythm Remains Within Normal Limits in the Microgravity Environment.

Brain sciences·2025
Same author

A New Perspective in Epileptic Seizure Classification: Applying the Taxonomy of Seizure Dynamotypes to Noninvasive EEG and Examining Dynamical Changes across Sleep Stages.

eNeuro·2025
Same author

Task-guided attention increases non-linearity of steady-state visually evoked potentials.

Journal of neural engineering·2024
Same author

Statistical modeling of adaptive neural networks explains co-existence of avalanches and oscillations in resting human brain.

Nature computational science·2024

Related Experiment Video

Updated: May 21, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.2K

Supervised autoencoder denoiser for non-stationarity in multi-session EEG-based BCI.

Avin Ofer1, Almagor Ophir1, Noah Yoav1

  • 1Department of Cognitive and Brain Sciences, Ben-Gurion University of the Negev, Beersheba, Israel.

Journal of Neural Engineering
|March 24, 2025
PubMed
Summary

This study introduces a novel supervised autoencoder to reduce session-specific noise in electroencephalogram (EEG) signals for brain-computer interfaces (BCIs). The method enhances BCI accuracy by effectively denoising non-stationary signals without needing new session data.

Keywords:
EEGautoencoderdenoisingmotor-imagery BCInon-stationarity

More Related Videos

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.6K

Related Experiment Videos

Last Updated: May 21, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.2K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.6K

Area of Science:

  • Neuroscience
  • Computer Science
  • Biomedical Engineering

Background:

  • Non-stationarity in electroencephalogram (EEG) signals presents significant challenges for brain-computer interface (BCI) performance.
  • Session-specific variability in EEG data often necessitates frequent recalibration, hindering practical BCI implementation.

Purpose of the Study:

  • To develop a novel method for cross-session BCI tasks that mitigates non-stationary variability in EEG signals.
  • To reduce session-specific information while preserving task-related signals for improved BCI accuracy.

Main Methods:

  • A supervised autoencoder was employed to compress and reconstruct high-dimensional EEG inputs.
  • The autoencoder's objective function included unsupervised reconstruction error minimization and supervised terms to remove session identity and optimize for classification.
  • The method was evaluated across three motor imagery datasets.

Main Results:

  • The proposed approach effectively addressed domain adaptation challenges in cross-session BCI tasks.
  • Performance surpassed both naïve cross-session and within-session methods on motor imagery datasets.
  • The method demonstrated successful reduction of session-specific information, denoising non-stationary signals.

Conclusions:

  • The novel method eliminates the need for new session data, making it unsupervised for new sessions and reducing recalibration needs.
  • Effective denoising of non-stationary EEG signals enhances BCI model accuracy.
  • Future applications may extend to other BCI tasks and analysis of residual signals for cognitive process investigation.