内容简介
基于频率-相位编码的SSVEP脑机接口系统
SSVEP有训练的主流算法
空间滤波器算法介绍
训练数据不足问题
多频率学习
空间滤波器算法的发展
总结
5 June 2020
2
基于频率-相位编码的SSVEP脑机接口系统
由清华大学团队提出的脑机接口范式
• 编码:通过观察闪烁刺激,用户的SSVEP信号会诱发出不同的频率和相位
• 解码:通过对SSVEP进行分析,判断最有可能的频率和相位信息
5 June 2020
3
Chen, X., et al. (2015). High-speed spelling with a noninvasive brain–computer interface. Proc. Natl. Acad. Sci. U. S. A, 112(44), E6058-E6067.
基于频率-相位编码的SSVEP脑机接口系统
由清华大学团队提出的脑机接口范式
❑优点:
• 信息传输率(ITR)高
• 用户不用长时间训练
❑需要改进的地方:
• 闪烁刺激容易造成视觉疲劳[1][2]
• 机器需要很多用户数据进行训练
5 June 2020
4
Chen, X., et al. (2015). High-speed spelling with a noninvasive brain–computer interface.
Proc. Natl. Acad. Sci. U. S. A, 112(44), E6058-E6067.
[1] Cao, T., et al. (2014). Objective evaluation of fatigue by EEG
spectral analysis in steady-state visual evoked potential-based brain-
computer interfaces. Biomedical engineering online, 13(1), 28.
[2] Peng, Y., et al. (2020). Changes of EEG phase synchronization
and EOG signals along the use of steady state visually evoked
potential-based brain computer interface. Journal of Neural
Engineering.
SSVEP有训练的主流算法
两个主流的算法:
• 典型相关分析(CCA)[1-5]
• 任务相关成分分析(TRCA)[6]
5 June 2020
5
[1] Nakanishi, M., et al. (2014). A high-speed brain speller using steady-state visual evoked potentials. Int. J. Neural Syst., 24(06), 1450019.
[2] Chen, X., et al. (2015). High-speed spelling with a noninvasive brain–computer interface. Proc. Natl. Acad. Sci. U.S.A., 112(44), E6058-E6067.
[3] Bin, G., et al. (2009). An online multi-channel SSVEP-based brain–computer interface using a canonical correlation analysis method. Journal of neural engineering, 6(4), 046002.
[4] Zhang, Y., et al. (2014). Frequency recognition in SSVEP-based BCI using multiset canonical correlation analysis. International journal of neural systems, 24(04), 1450013.
[5] Chen, X., et al. (2015). Filter bank canonical correlation analysis for implementing a high-speed SSVEP-based brain–computer interface. Journal of neural engineering, 12(4), 046008.
[6] Nakanishi, M., et al. (2017). Enhancing detection of SSVEPs for a high-speed brain speller using task-related component analysis. IEEE Transactions on Biomedical Engineering, 65(1),
104-112.
ITR超过200bits/min!
评论13