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

Starch and tuber traits of diploid potato lines B26 and B100 and their hybrids.

BMC plant biology·2026
Same author

Kolmogorov-Arnold Networks for Sensor Data Processing: A Comprehensive Survey of Architectures, Applications, and Open Challenges.

Sensors (Basel, Switzerland)·2026
Same author

Continuous glucose monitoring trajectories in patients with acute coronary syndrome.

Cardiovascular diabetology·2026
Same author

A comparative study of industrial and open-source SCADAs to optimize the design of control systems for the IFMIF-DONES plant.

Scientific reports·2026
Same author

Cogformer: A Unified Multi-Scale Brain Representation for Visual Decoding and Reconstruction From fMRI.

IEEE transactions on medical imaging·2026
Same author

Advancing skin cancer detection through deep learning and fusion of patient metadata and skin lesion images.

Scientific reports·2026

Related Experiment Video

Updated: Dec 18, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

1.6K

Deep learning for EEG-based Motor Imagery classification: Accuracy-cost trade-off.

Javier León1, Juan José Escobar1, Andrés Ortiz2

  • 1Department of Computer Architecture and Technology, University of Granada, Granada, Spain.

Plos One
|June 12, 2020
PubMed
Summary

Genetic Algorithms optimize shallow Artificial Neural Networks (ANNs) for Electroencephalography (EEG) data, improving accuracy while considering computational cost. Smaller networks can match larger ones, highlighting potential overfitting in deep learning for EEG-BCI applications.

More Related Videos

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

43.9K
Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients
09:42

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

1.9K

Related Experiment Videos

Last Updated: Dec 18, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

1.6K
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

43.9K
Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients
09:42

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

1.9K

Area of Science:

  • Neuroscience
  • Computer Science
  • Machine Learning

Background:

  • Electroencephalography (EEG) datasets are typically small and high-dimensional, posing challenges for machine learning.
  • Artificial Neural Networks (ANNs) show promise in EEG-based Brain-Computer Interface (BCI) applications but require computationally intensive training and optimization.
  • The trade-off between model performance (quality) and computational resources (cost) is often overlooked in EEG analysis.

Purpose of the Study:

  • To apply Genetic Algorithms for hyperparameter optimization of shallow Artificial Neural Networks (ANNs) including Convolutional Neural Networks (CNNs), Feed-Forward Neural Networks (FFNNs), and Recurrent Neural Networks (RNNs).
  • To compare the performance, energy consumption, and training time of optimized shallow ANNs.
  • To analyze the relationship between network size, structural complexity, and accuracy, especially in the context of limited EEG data.

Main Methods:

  • Utilized Genetic Algorithms to optimize hyperparameters for shallow CNNs, FFNNs, and RNNs.
  • Compared the accuracy, energy consumption, and training time of various optimized ANN architectures.
  • Evaluated network performance against a 6-layer Deep Belief Network (DBN).

Main Results:

  • Hyperparameter optimization using Genetic Algorithms improved accuracy across all tested ANN models.
  • Shallow CNNs with a single hidden convolutional layer achieved performance comparable to or exceeding a 6-layer DBN.
  • FFNNs and RNNs offered significantly lower computational costs but did not reach the same accuracy levels as CNNs.
  • Network size did not consistently correlate with accuracy; smaller models sometimes outperformed larger ones, suggesting overfitting issues with limited data.

Conclusions:

  • Genetic Algorithm-based optimization is effective for improving ANN performance in EEG analysis.
  • Shallow CNNs present an efficient alternative to deeper architectures for EEG-BCI tasks, balancing accuracy and computational cost.
  • Careful consideration of model complexity and potential overfitting is crucial when working with small, high-dimensional EEG datasets.