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

Real time fault diagnosis in industrial robotics using discrete and slantlet wavelet transformations.

Scientific reports·2025

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 1, 2025

Multiscale Investigations of Cortical Processing by Integrating Laminar Polytrodes and Optogenetics with Micro Electrocorticography in Rodents

Multiscale Investigations of Cortical Processing by Integrating Laminar Polytrodes and Optogenetics with Micro Electrocorticography in Rodents

Published on: May 23, 2025

CutCat: An augmentation method for EEG classification.

Ali Al-Saegh¹, Shefa A Dawwd¹, Jassim M Abdul-Jabbar¹

¹Computer Engineering Department, College of Engineering, University of Mosul, Mosul, Iraq.

Neural Networks : the Official Journal of the International Neural Network Society

|June 20, 2021

Summary

This study introduces CutCat, a novel data augmentation method for electroencephalogram (EEG) datasets. CutCat enhances deep learning model performance in classifying motor imagery (MI) EEG signals, even with limited data.

Keywords:

Augmentation BCI CNN Deep learning EEG Motor imagery

More Related Videos

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Published on: June 6, 2015

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping

Published on: June 26, 2012

Related Experiment Videos

Last Updated: Nov 1, 2025

Multiscale Investigations of Cortical Processing by Integrating Laminar Polytrodes and Optogenetics with Micro Electrocorticography in Rodents

Multiscale Investigations of Cortical Processing by Integrating Laminar Polytrodes and Optogenetics with Micro Electrocorticography in Rodents

Published on: May 23, 2025

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Published on: June 6, 2015

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping

Published on: June 26, 2012

Area of Science:

Neuroscience
Machine Learning
Signal Processing

Background:

Electroencephalogram (EEG) signals offer non-invasive human-device communication.
Deep learning excels at feature extraction and classification but requires extensive data.
Limited EEG data hinders the application of deep learning in this domain.

Purpose of the Study:

To propose a novel data augmentation method, CutCat, to enlarge EEG datasets.
To address the challenge of small-scale datasets in EEG research.
To improve the classification accuracy of motor imagery (MI) EEG signals.

Main Methods:

Developed the CutCat augmentation method by concatenating segments from different EEG trials.
Applied CutCat to generate synthetic data for inter- and intra-subject variability.
Utilized Convolutional Neural Networks (CNNs) with both time-series and image (STFT-generated) data inputs.

Main Results:

The CutCat method effectively increased the size of EEG datasets.
Tested CNN models demonstrated improved classification performance on small-scale EEG datasets.
The augmentation strategy showed promising results compared to state-of-the-art methods.

Conclusions:

The CutCat augmentation method is a viable strategy for enhancing EEG datasets.
This approach facilitates the effective application of deep learning for EEG signal classification with limited data.
The findings suggest a pathway for advancing EEG-based brain-computer interfaces.