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 Video

Updated: May 6, 2026

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI
10:35

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI

Published on: June 3, 2013

36.3K

Robust common spatial filters with a max-min approach.

Motoaki Kawanabe1, Wojciech Samek, Klaus-Robert Müller

  • 1ATR Brain Information Communication Research Laboratory Group, Soraku-gun, Kyoto 619-0288, Japan kawanabe@atr.jp.

Neural Computation
|November 12, 2013
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

Towards robust foundation models for digital pathology.

Nature communications·2026
Same author

Beyond attention heatmaps: How to get better explanations for multiple instance learning models in histopathology.

Medical image analysis·2026
Same author

Prediction of an fMRI-based schizophrenia biomarker from EEG using dynamic functional connectivity: a simultaneous EEG-fMRI study.

Biomedical physics & engineering express·2026
Same author

AI-based discovery of functional boundaries in the human brain from intraoperative electrophysiology.

medRxiv : the preprint server for health sciences·2026
Same author

Canonical coherence for the estimation of within- and cross-frequency cortico-kinematic interactions.

Scientific reports·2026
Same author

Modeling attention and binding in the brain through bidirectional recurrent gating.

Nature communications·2026

This study introduces a robust Common Spatial Patterns (CSP) algorithm using a maxmin approach to improve electroencephalographic signal analysis. This method enhances brain-computer interface accuracy by reducing noise and overfitting.

Area of Science:

  • Neuroscience
  • Signal Processing
  • Machine Learning

Background:

  • Electroencephalographic (EEG) signals are nonstationary and susceptible to artifacts, necessitating noise-robust analysis methods.
  • Standard Common Spatial Patterns (CSP) algorithm relies on single covariance matrix estimates, making it vulnerable to outliers and overfitting.

Purpose of the Study:

  • To develop a robust version of the CSP algorithm for analyzing noisy and nonstationary EEG data.
  • To enhance the performance of brain-computer interfaces (BCIs) by improving feature extraction from EEG signals.

Main Methods:

  • Proposed a maxmin approach to robustly compute spatial filters by maximizing the minimum variance ratio within a tolerance set of covariance matrices.
  • Introduced a data-driven method to construct a tolerance set capturing covariance matrix variability over time.

More Related Videos

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters
14:58

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters

Published on: June 2, 2010

9.1K

Related Experiment Videos

Last Updated: May 6, 2026

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI
10:35

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI

Published on: June 3, 2013

36.3K
Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters
14:58

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters

Published on: June 2, 2010

9.1K
  • Tested the robust CSP filters on real-world BCI data and compared them with standard CSP and a state-of-the-art method.

    • Main Results:

    • The maxmin optimization demonstrated robustness to outliers and reduced overfitting in CSP.
    • The data-driven tolerance set construction reduced feature nonstationarity and significantly improved classification accuracy.
    • Simulations investigated the advantages and limitations of the maxmin approach.

    Conclusions:

    • The maxmin CSP approach offers a robust and effective method for analyzing nonstationary EEG signals, particularly for BCI applications.
    • This robustification technique improves feature extraction and classification accuracy in the presence of noise and signal variability.