Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Brain-Computer Interface Training Fosters Perceptual Skills to Detect Errors.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

The dual nature of alpha oscillations: Linking local rhythms to network function and dysfunction.

Neuroscience and biobehavioral reviews·2026

Same author

The predictive brain: Neural correlates of word expectancy align with large language model prediction probabilities.

NeuroImage·2026

Same author

Decoloniality impact assessment for AI.

AI & society·2026

Same author

Correction to: Towards Network-Based Neurofeedback of Visual Areas to Enhance Visual Perception.

Brain topography·2026

Same author

LINA's testing infrastructure enables AI to take-off in unmanned aerial vehicles (UAVs).

Frontiers in robotics and AI·2026

Search research articles

Related Experiment Video

Updated: Dec 20, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Spatial covariance improves BCI performance for late ERPs components with high temporal variability.

Ruslan Aydarkhanov¹, Marija Ušćumlić², Ricardo Chavarriaga^3,4

¹Medical Image Processing Laboratory, Center for Neuroprosthetics, Interschool Institute of Bioengineering, École Polytechnique Fédérale de Lausanne (EPFL), Campus Biotech H4, 1202 Geneva, Switzerland.

Journal of Neural Engineering

|May 23, 2020

Summary

Spatial covariance features offer stable Event-Related Potential (ERP) decoding, outperforming traditional waveform methods, especially in challenging brain-computer interface tasks with high variability and across different experimental protocols.

More Related Videos

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

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

Published on: October 24, 2012

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

Published on: May 7, 2014

Related Experiment Videos

Last Updated: Dec 20, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

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

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

Published on: October 24, 2012

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

Published on: May 7, 2014

Area of Science:

Neuroscience
Signal Processing
Biomedical Engineering

Background:

Event-Related Potentials (ERPs) are crucial for brain-computer interfaces (BCIs), reflecting cognitive responses to stimuli.
Classical ERP decoding relies on waveform characteristics (latency, amplitude), requiring precise time- and phase-locking across trials.
Challenges arise in complex tasks or when generalizing across conditions, leading to performance degradation due to latency jitter and delays.

Purpose of the Study:

To evaluate the performance stability of spatial covariance-based features versus traditional waveform features for ERP decoding.
To assess the efficacy of these features in scenarios involving generalization across experiments and increased latency jitter.
To determine if combining features enhances decoding performance.

Main Methods:

Comparison of waveform and covariance-based features in two simulated scenarios: generalization across Error-related Potentials (ErrP) experiments and handling significant latency jitter.
Quantitative analysis of decoding performance (Area Under the Curve - AUC) under varying jitter levels (up to ±300 ms).

Main Results:

Covariance-based features demonstrated robust performance, maintaining stability even with ±300 ms jitter, unlike waveform features which dropped significantly (0.85 to 0.55 AUC).
Covariance features also showed superior generalization capabilities across different ErrP experimental protocols.
Combined features were not explicitly detailed in the abstract but implied as part of the comparison.

Conclusions:

Spatial covariance features provide more reliable ERP classification, particularly for signals with high intrinsic variability in demanding BCI applications.
These features enable robust generalization across related experimental protocols, overcoming limitations of traditional waveform analysis.
Covariance-based approaches represent a significant advancement for BCI performance and applicability in real-world scenarios.