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 Experiment Videos

User's Self-Prediction of Performance in Motor Imagery Brain-Computer Interface.

Minkyu Ahn1, Hohyun Cho2, Sangtae Ahn3

  • 1School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea.

Frontiers in Human Neuroscience
|March 3, 2018
PubMed
Summary

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

Editorial: Deep learning in brain-computer interfaces.

Frontiers in human neuroscience·2026
Same author

Aperiodic and oscillatory activity of the human brain during induced emotional states.

medRxiv : the preprint server for health sciences·2026
Same author

Neural network architectures and normalization techniques for automated sleep stage classification using rodent EEG and EMG signals.

PloS one·2026
Same author

Adversarially regularized transformer with channel-wise noise for robust hand gesture recognition using surface electromyography.

Biomedical engineering letters·2026
Same author

EEG dataset of consumer- and research-grade systems.

Scientific data·2026
Same author

A comprehensive evaluation framework for consumer-grade EEG devices: signal quality, robustness, and usability.

Scientific reports·2026

Users can accurately predict their motor imagery brain-computer interface (MI-BCI) performance without feedback. This self-prediction ability improves with task experience, suggesting the brain actively senses performance quality.

Area of Science:

  • Neuroscience
  • Human-Computer Interaction
  • Biomedical Engineering

Background:

  • Motor imagery brain-computer interface (MI-BCI) performance varies significantly among users.
  • Predicting MI-BCI performance is crucial for prescreening and optimizing user selection.
  • Few studies have explored users' self-assessment and prediction of their own MI-BCI performance.

Purpose of the Study:

  • To investigate the feasibility of using user self-prediction to estimate MI-BCI performance.
  • To determine if users can accurately gauge their MI-BCI capabilities without external feedback.
  • To analyze how task experience influences the accuracy of self-predicted MI-BCI performance.

Main Methods:

  • Fifty-two participants performed a two-class motor imagery task with electroencephalogram (EEG) recording.
Keywords:
BCIBCI-illiteracymotor imageryperformance variationprediction

Related Experiment Videos

  • Participants provided subjective ratings on task difficulty and predicted their MI-BCI performance.
  • Offline classification accuracy was calculated from EEG data and compared with self-predictions and questionnaire scores.

    • Main Results:

    • User self-predictions of MI-BCI performance showed a significant positive correlation with actual performance (r = 0.64, p < 0.01).
    • The accuracy of self-prediction improved as participants completed more motor imagery tasks.
    • Correlation coefficients increased from 0.02 (pre-task) to 0.54 (2nd run), and root mean square error decreased from 17.7% to 10% (3rd run).

    Conclusions:

    • Subjects can accurately predict their own MI-BCI performance without receiving feedback.
    • The human brain acts as an active learning system, sensing and adapting to the quality of the motor imagery process.
    • User self-prediction offers a viable method for estimating MI-BCI performance, aiding in understanding and mitigating performance variability.