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

Preserved Aesthetic Judgements in Parkinson's Disease: A Case-Control Study Suggests Limited Need for Content Adaptation for Receptive Arts Engagement.

Journal of clinical medicine·2026
Same author

Uses of assistive technology incorporating smart camera features in the rehabilitation of people living with disabilities: a scoping review.

Disability and rehabilitation. Assistive technology·2026
Same author

An online brain-computer interface for detecting incongruity in augmented reality applications.

Journal of neural engineering·2026
Same author

Turning motor intentions into words: an MRCP-based BCI speller for motor-impaired users enhanced by task-specific calibration.

Journal of neural engineering·2026
Same author

Opposing cortical forces: Alpha slowing and sensorimotor mu acceleration during motor-related BCI training.

PLoS computational biology·2026
Same author

Toward the Automatic Detection of Vection in Virtual Reality Using EEG.

IEEE transactions on visualization and computer graphics·2026

Related Experiment Video

Updated: Apr 15, 2026

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks
11:31

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

Published on: December 5, 2014

15.8K

Random forests in non-invasive sensorimotor rhythm brain-computer interfaces: a practical and convenient non-linear

David Steyrl, Reinhold Scherer, Josef Faller

    Biomedizinische Technik. Biomedical Engineering
    |April 2, 2015
    PubMed
    Summary

    Random forest (RF) classifiers are practical for brain-computer interfaces (BCIs). This study shows RFs are effective for sensorimotor rhythm (SMR) BCIs, outperforming linear classifiers and demonstrating online applicability.

    More Related Videos

    Assessment and Communication for People with Disorders of Consciousness
    07:37

    Assessment and Communication for People with Disorders of Consciousness

    Published on: August 1, 2017

    9.7K
    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
    06:37

    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

    Published on: July 14, 2023

    1.4K

    Related Experiment Videos

    Last Updated: Apr 15, 2026

    Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks
    11:31

    Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

    Published on: December 5, 2014

    15.8K
    Assessment and Communication for People with Disorders of Consciousness
    07:37

    Assessment and Communication for People with Disorders of Consciousness

    Published on: August 1, 2017

    9.7K
    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
    06:37

    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

    Published on: July 14, 2023

    1.4K

    Area of Science:

    • Neuroscience
    • Machine Learning
    • Biomedical Engineering

    Background:

    • Linear classifiers are preferred in brain-computer interface (BCI) research due to parameter complexity in non-linear methods.
    • Random Forest (RF) classifiers, while popular in other fields, are underutilized in BCI applications.
    • Existing research has not fully explored the potential of RFs for sensorimotor rhythm (SMR) based BCIs.

    Purpose of the Study:

    • To investigate the parametrization, online applicability, and performance of Random Forest (RF) classifiers in SMR-BCIs.
    • To compare the efficacy of RFs against regularized linear discriminant analysis (LDA) in SMR-BCI.
    • To establish RFs as a viable and convenient non-linear classifier for SMR-BCI systems.

    Main Methods:

    • Investigated RF parametrization, demonstrating performance stability across a wide parameter range.
    • Validated the online applicability of RF classifiers in SMR-BCI for the first time.
    • Conducted offline BCI simulations to compare RF performance against regularized LDA.

    Main Results:

    • RF classifier performance remained consistent across various parameter settings.
    • Demonstrated the successful online application of RFs in SMR-BCIs.
    • RFs statistically significantly outperformed regularized LDA by approximately 3% in offline simulations.

    Conclusions:

    • Random Forest (RF) classifiers are practical, convenient, and high-performing non-linear classifiers for SMR-BCIs.
    • RFs offer advantages such as feature distribution independence and multiclass capabilities, making them suitable for future BCI development.
    • The findings support the increased consideration and adoption of RFs in advanced BCI research and applications.