Development of novel attention galibration protocols for EEG-based BCI system
Attention is important in our lives to achieve optimal task performance. To improve our attention, we can go through attention training. Attention training can provide many benefits, such as improving the conditions of attention deficit hyperactivity disorder (ADHD), or improving safety in high-risk...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
Nanyang Technological University
2021
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/147990 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | Attention is important in our lives to achieve optimal task performance. To improve our attention, we can go through attention training. Attention training can provide many benefits, such as improving the conditions of attention deficit hyperactivity disorder (ADHD), or improving safety in high-risk jobs such as nuclear plant operators. In order to use a brain computer interface (BCI) for attention training, a calibration process to derive the electroencephalogram (EEG) signals of the current user’s attentive and inattentive states is required. The collected data from calibration will be used to train a support-vector machine (SVM), which will provide real-time classification of the user’s attention states. However, the existing calibration protocol contain non-insignificant inaccuracies, which may affect the performance of the BCI after calibration. This paper proposes a new, novel audio-visual protocol for calibrating the BCI for attention training apps. An experiment was designed to compare the performance of the proposed protocol against the existing protocol. In total, 16 subjects participated in the experiment. Results from the experiment concludes that the proposed protocol performs better than the existing protocol, but the difference between the two is not significant. |
|---|