Related Experiment Video
Updated: Jan 3, 2026
06:34
A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
Published on: July 7, 2023
3.1K
Robustness analysis of decoding SSVEPs in humans with head movements using a moving visual flicker
Suguru Kanoga1, Masaki Nakanishi, Akihiko Murai
1Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology (AIST), Tokyo 135-0064, Japan. Author to whom any correspondence should be addressed.
Journal of Neural Engineering
|November 14, 2019
Summary
Mobile brain-computer interfaces (BCIs) using electroencephalogram (EEG) can work even with head movements. Muscular artifacts from head motion slightly reduce signal quality but BCI accuracy remains high for practical applications.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Signal Processing
Background:
- Mobile electroencephalogram (EEG) platforms are expanding brain-computer interface (BCI) applications beyond laboratory settings into daily life.
- Unrestrained natural behaviors, such as head movements, can introduce artifacts that degrade BCI performance.
- This study investigates the impact of muscular artifacts from head movements on steady-state visual evoked potentials (SSVEPs) used in BCIs.
Purpose of the Study:
- To explore the effect of muscular artifacts generated by head movements on SSVEP signal characteristics.
- To evaluate the impact of these artifacts on the classification performance of SSVEP-based BCIs.
- To determine the feasibility of using SSVEPs in real-world mobile BCI applications with unrestricted head motion.
Main Methods:
- Induced SSVEPs and controlled horizontal/vertical head movements using a visual flicker stimulus.
- Utilized a laser feedback system to guide head movements independently of eye movements.
- Quantified SSVEP amplitude and signal-to-noise ratio (SNR), and assessed frequency identification accuracy using calibration-free and fully-calibrated algorithms.
Main Results:
- Head movements, particularly vertical ones, significantly deteriorated SSVEP amplitude and SNR.
- Frequency identification accuracy decreased proportionally with the speed of head movements.
- Importantly, accuracy remained significantly above chance level despite artifact contamination and varying algorithms.
Conclusions:
- Decoding SSVEPs is feasible even with participants freely moving their heads.
- The findings support the practical application of mobile BCIs in real-world scenarios.
- Mobile BCIs can be robust to muscular artifacts induced by natural head movements.
