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

Online decoding of rat self-paced locomotion speed from EEG using recurrent neural networks.

Journal of neural engineering·2026
Same author

Comparative study of combustion and pollutant emission characteristics of sludges with different drying methods in a simulated municipal solid waste grate furnace combustion process.

Waste management (New York, N.Y.)·2026
Same author

Factors that influence the amplitude of the bereitschaftspotential.

Neuroscience and biobehavioral reviews·2026
Same author

Mid-level perceptual features, and not ambiguity, accelerate access to awareness.

Neuroscience of consciousness·2026
Same author

A multi-measurement study of the relation between deliberation and volition.

Neuroscience of consciousness·2025
Same author

Probing for intentions: The early readiness potential does not reflect awareness of motor preparation.

Imaging neuroscience (Cambridge, Mass.)·2025
Same journal

Detection of cochlear microphonic for differential diagnosis between auditory neuropathy mice and noise-induced sensorineural hearing loss mice.

Journal of neuroscience methods·2026
Same journal

Assessment metrics for pain control in rats: A methodological commentary.

Journal of neuroscience methods·2026
Same journal

Infant EEG preprocessing pipelines: A capability framework and current gaps in practice.

Journal of neuroscience methods·2026
Same journal

Methods for Measuring Neural Activity During Voluntary Wheel Running.

Journal of neuroscience methods·2026
Same journal

Serotype-dependent differences in AAV cellular transduction rates in the hypothalamus of Arctic ground squirrels.

Journal of neuroscience methods·2026
Same journal

Rapid generation of human sensory neurons from iPSC for modeling of peripheral neuropathies.

Journal of neuroscience methods·2026
See all related articles

Related Experiment Video

Updated: Dec 13, 2025

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

5.9K

Data augmentation for deep-learning-based electroencephalography.

Elnaz Lashgari1, Dehua Liang1, Uri Maoz2

  • 1Schmid College of Science and Technology, Chapman University, United States; Institute for Interdisciplinary Brain and Behavioral Sciences, Chapman University, United States.

Journal of Neuroscience Methods
|August 4, 2020
PubMed
Summary
This summary is machine-generated.

Data augmentation significantly enhances deep learning models for electroencephalography (EEG) tasks. Techniques like noise addition and sliding windows offer substantial accuracy improvements, particularly for mental workload analysis.

Keywords:
Data augmentationDeep learningElectroencephalographyReview

More Related Videos

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

2.8K
High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources
12:39

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

Published on: November 26, 2016

16.5K

Related Experiment Videos

Last Updated: Dec 13, 2025

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

5.9K
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

2.8K
High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources
12:39

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

Published on: November 26, 2016

16.5K

Area of Science:

  • Neuroscience
  • Computer Science
  • Machine Learning

Background:

  • Deep learning (DL) models often struggle with electroencephalography (EEG) data due to a low samples-to-features ratio.
  • Data augmentation (DA) techniques can significantly improve DL model accuracy, stability, and reduce overfitting in various applications.
  • DA holds transformative potential for EEG processing, mirroring its impact on fields like computer vision.

Purpose of the Study:

  • To review existing trends and approaches in data augmentation (DA) for deep learning (DL) applied to electroencephalography (EEG) data.
  • To identify common DA techniques used for specific EEG tasks and the input features involved.
  • To quantify the expected accuracy gains achievable through DA in EEG analysis.

Main Methods:

  • A systematic review of DA techniques applied to DL for EEG.
  • Categorization of DA methods including noise addition, generative adversarial networks, sliding windows, sampling, Fourier transform, and segmentation recombination.
  • Classification of EEG tasks into seizure detection, sleep stages, motor imagery, mental workload, emotion recognition, motor tasks, and visual tasks.

Main Results:

  • Data augmentation for DL on EEG has been steadily increasing over the past five years.
  • Noise addition and sliding windows demonstrated the highest accuracy boosts, with mental workload tasks showing the greatest benefit from DA.
  • Specific techniques like sliding window, noise addition, and sampling are frequently used for seizure detection, mental workload, and sleep stage classification, respectively.

Conclusions:

  • Data augmentation is increasingly utilized and demonstrably improves DL decoding accuracy for EEG data.
  • The average accuracy gain from DA across various EEG tasks is approximately 29%, with specific methods yielding higher improvements.
  • Adherence to reporting guidelines in future publications will enable more comprehensive analyses of DA's impact on EEG.