Related Experiment Video
Updated: May 13, 2026
06:34
A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
Published on: July 7, 2023
Classification of binary intentions for individuals with impaired oculomotor function: 'eyes-closed' SSVEP-based
Jeong-Hwan Lim1, Han-Jeong Hwang, Chang-Hee Han
1Department of Biomedical Engineering, Hanyang University, Seoul 133-731, Korea.
Journal of Neural Engineering
|March 27, 2013
Summary
This study introduces an "eyes-closed" brain-computer interface (BCI) using steady-state visual evoked potentials (SSVEP) for individuals with severe neuromuscular diseases. The novel system enables communication for those with impaired oculomotor function.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Rehabilitation Technology
Background:
- Patients with severe neuromuscular diseases often have impaired oculomotor control, limiting their use of traditional brain-computer interface (BCI) systems.
- Existing steady-state visual evoked potential (SSVEP)-based BCIs typically require users to maintain open eyes and gaze at visual stimuli, posing a challenge for individuals with conditions like amyotrophic lateral sclerosis (ALS).
Purpose of the Study:
- To develop and validate a novel SSVEP-based BCI paradigm that functions with the user's eyes closed.
- To enable communication for individuals with severe neuromuscular diseases and impaired oculomotor function.
Main Methods:
- Developed an electroencephalography (EEG)-based BCI system utilizing flickering light-emitting diodes (LEDs) presented to participants with their eyes closed.
- Conducted offline experiments with 11 participants and online experiments with 5 healthy participants and 1 ALS patient to classify EEG patterns and binary intentions.
Main Results:
- Confirmed that SSVEP can be modulated by selective visual attention through closed eyelids, achieving classification accuracy suitable for practical BCI use.
- Online experiments with healthy participants demonstrated real-time binary intention classification with an average information transfer rate of 10.83 bits/min.
- A preliminary online test with an ALS patient achieved an 80% classification accuracy.
Conclusions:
- The proposed 'eyes-closed' SSVEP-based BCI paradigm is feasible and effective for individuals with impaired oculomotor function.
- This innovative BCI system holds significant potential for enhancing communication capabilities in disabled individuals with severe neuromuscular diseases.
