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

The AHEPA EEG benchmark: setting the standard for machine learning in dementia diagnosis, a scoping review.

Cognitive neurodynamics·2026
Same author

The exposome of brain aging across 34 countries.

Nature medicine·2026
Same author

Psychosocial factors and predictors of stigma in individuals diagnosed with epilepsy: a cross-sectional study.

Psychology, health & medicine·2026
Same author

Effectiveness and Safety of Teduglutide Treatment in Adult Patients with Short Bowel Syndrome: A Case Series and Review of Current Evidence.

Journal of clinical medicine·2026
Same author

Beyond the Exome: The Role of Noncoding and Regulatory Variants in Monogenic Diseases.

Current issues in molecular biology·2026
Same author

Constructing Artificial Features with Grammatical Evolution for the Motor Symptoms of Parkinson's Disease.

Bioengineering (Basel, Switzerland)·2025

Related Experiment Video

Updated: Nov 10, 2025

Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content
10:41

Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content

Published on: May 26, 2018

7.1K

EEG-Based Eye Movement Recognition Using Brain-Computer Interface and Random Forests.

Evangelos Antoniou1, Pavlos Bozios1, Vasileios Christou1,2

  • 1Department of Informatics and Telecommunications, University of Ioannina, GR47100 Arta, Greece.

Sensors (Basel, Switzerland)
|April 3, 2021
PubMed
Summary

This study developed a novel brain-computer interface (BCI) using random forests to classify eye movements from EEG signals for wheelchair control. The system achieved 85.39% accuracy, offering a promising non-manual navigation solution.

Keywords:
EEGEPOC Flexbrain–computer interfaceelectroencephalogramelectrooculogrameye movementeye trackingrandom forests

More Related Videos

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
07:43

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

8.0K
Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking
07:26

Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking

Published on: September 26, 2019

8.1K

Related Experiment Videos

Last Updated: Nov 10, 2025

Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content
10:41

Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content

Published on: May 26, 2018

7.1K
Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
07:43

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

8.0K
Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking
07:26

Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking

Published on: September 26, 2019

8.1K

Area of Science:

  • Neuroscience and Biomedical Engineering
  • Human-Computer Interaction
  • Rehabilitation Technology

Background:

  • There is a growing need for non-manual control systems for wheelchairs, particularly for individuals with mobility impairments.
  • Brain-computer interfaces (BCIs) offer a potential solution by translating neural signals into commands.
  • Discriminating eye movements and visual states via electroencephalography (EEG) is crucial for developing intuitive BCI systems.

Purpose of the Study:

  • To present a novel brain-computer interface (BCI) system for classifying eye movements into six categories using electroencephalographic (EEG) signals.
  • To evaluate the efficacy of the random forests (RF) classification algorithm for this BCI application.
  • To demonstrate the potential of the developed system for controlling an electromechanical wheelchair.

Main Methods:

  • EEG signals were captured from 10 patients using the EPOC Flex head cap with 32 sensors.
  • Signals were processed into 4-second windows, and band energy was extracted for delta, theta, alpha, and beta brain waves.
  • A random forests (RF) algorithm was employed to classify eye states (open, closed, left, right, up, down) and compared against other machine learning algorithms.

Main Results:

  • The proposed random forests brain-computer interface (RF-BCI) achieved a high accuracy of 85.39% for a 6-class classification task.
  • The RF algorithm demonstrated superior performance compared to Naïve Bayes, Bayes Network, K-NN, MLP, SVM, J48-C4.5, and Bagging algorithms.
  • The system successfully utilized spatial information from the Emotiv EPOC Flex device for BCI wheelchair technology.

Conclusions:

  • The developed RF-BCI system is effective for discriminating eye movements and visual states from EEG signals.
  • This approach provides a viable non-manual control method for electromechanical wheelchairs and rehabilitation devices.
  • The Emotiv EPOC Flex wearable EEG device shows significant potential for BCI-based wheelchair navigation applications.