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

Machine Learning for Diagnosis and Differentiation of Central Disorders of Hypersomnolence: A Systematic Review.

European journal of neurology·2026
Same author

Phenotyping of Patients with Age-Related Macular Degeneration Using Artificial Intelligence-Driven Biomarker Patterns in OCT.

Ophthalmology science·2026
Same author

Comorbidity Classification from Clinical Free-Text using Large Language Models: Application to Sleep Disorder Patients.

Journal of medical systems·2026
Same author

iSPHYNCS: Unsupervised Clustering in Questionnaires and Metadata Reveals Distinct Subtypes in the Narcolepsy Borderland.

Journal of sleep research·2026
Same author

Geographic Atrophy Structure-Function Relationships Based on Loss of OCT Outer Retinal Bands and Fundus Autofluorescence.

Ophthalmology science·2026
Same author

Directed cortico-limbic dialogue in the human brain.

Nature communications·2026

Related Experiment Video

Updated: Oct 19, 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

43.6K

Convolutional neural networks for decoding electroencephalography responses and visualizing trial by trial changes in

Florence M Aellen1, Pinar Göktepe-Kavis1, Stefanos Apostolopoulos2

  • 1Institute of Computer Science, University of Bern, Switzerland.

Journal of Neuroscience Methods
|September 26, 2021
PubMed
Summary

This study introduces a new deep learning pipeline for analyzing electroencephalography (EEG) data. It effectively classifies brain activity, even when neural responses shift, offering insights into trial-by-trial brain patterns.

Keywords:
ClassificationConvolutional neural networksDeep learningElectroencephalographyFeature extractionMultivariate pattern analysis

More Related Videos

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.1K
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

14.8K

Related Experiment Videos

Last Updated: Oct 19, 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

43.6K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.1K
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

14.8K

Area of Science:

  • Neuroscience
  • Machine Learning
  • Signal Processing

Background:

  • Deep learning, particularly Convolutional Neural Networks (CNNs), excels in computer vision but is less explored in electroencephalography (EEG) for multivariate pattern analysis (MVPA).
  • Traditional MVPA methods in EEG often use linear algorithms, assuming consistent neural responses across trials, which may underestimate dynamic brain activity.
  • Neural responses can vary in time and space during experiments, posing a challenge for conventional analysis techniques.

Purpose of the Study:

  • To develop and evaluate a novel deep learning pipeline using CNNs for classifying EEG responses to external stimuli.
  • To leverage CNNs to capture time- and space-unlocked neural activity for improved EEG data analysis.
  • To examine the trial-by-trial evolution of discriminant features in EEG data.

Main Methods:

  • A novel pipeline integrating data augmentation, CNN training, and feature visualization tailored for EEG MVPA was developed.
  • The pipeline was designed to handle dynamic neural activity that shifts in time and space across trials.
  • Convolutional Neural Networks (CNNs) were employed to extract complex patterns from EEG datasets.

Main Results:

  • The developed pipeline achieved high classification performance on EEG data and demonstrated generalization to new datasets.
  • Features identified by the CNN were found to be electrophysiologically interpretable.
  • The pipeline enabled the reconstruction of discriminant features at the single-trial level, allowing for the study of evolving brain activity.

Conclusions:

  • A novel deep learning pipeline for MVPA of EEG data was successfully developed.
  • The pipeline effectively extracts trial-by-trial discriminative activity in a data-driven manner, outperforming traditional MVPA algorithms.
  • This approach offers a powerful tool for analyzing dynamic neural responses in EEG research.