A Hybrid Speller Design Using Eye Tracking and SSVEP Brain-Computer Interface
Malik M Naeem Mannan1, M Ahmad Kamran1, Shinil Kang2,3
1Department of Cogno-Mechatronics Engineering, Pusan National University, 2 Busandaehak-ro, 63 Beon-gil, Geumjeong-gu, Busan 609-735, Korea.
Sensors (Basel, Switzerland)
|February 13, 2020
Summary
This study introduces a hybrid brain-computer interface (BCI) using electroencephalography (EEG) and eye-tracking. The novel system enhances user comfort while achieving high accuracy and information transfer rates for communication.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Human-Computer Interaction
Background:
- Steady-state visual evoked potentials (SSVEPs) are crucial for brain-computer interfaces (BCIs) due to their robustness and high information transfer rates (ITRs).
- However, traditional SSVEP BCIs often lead to user discomfort and fatigue when using numerous simultaneous flickering stimuli.
Purpose of the Study:
- To develop a stimuli-responsive hybrid speller integrating electroencephalography (EEG) and video-based eye-tracking.
- To enhance user comfort by reducing the number of required flickering frequencies for a large number of targets.
Main Methods:
- A hybrid BCI system combining EEG and eye-tracking was designed.
- Canonical Correlation Analysis (CCA) was employed to identify target frequencies with a 1-second signal duration.
- The system utilized only six frequencies to classify 48 distinct targets.
Main Results:
- The hybrid speller achieved an average classification accuracy of 90.35 ± 3.597%.
- Average ITRs were 184.06 ± 12.761 bits per minute (cued-spelling) and 190.73 ± 17.849 bits per minute (free-spelling).
- The system demonstrated superior performance in target classification, accuracy, and ITR compared to existing SSVEP spellers, with reduced user fatigue.
Conclusions:
- The proposed hybrid eye-tracking and SSVEP BCI system offers a more comfortable and efficient communication channel.
- This innovative approach significantly improves upon traditional SSVEP BCI limitations, enabling high-speed communication with increased user well-being.
