基于ssVEP与眼动追踪的混合型并行脑机接口研究

Research on Hybrid Parallel Brain-Computer Interface Based on ssVEP and Eye Tracking

针对目前单一脑机接口系统在指令分类正确率与信息传输速率较低的问题,搭建硬件并行EEG-ET采集系统,对基于稳态视觉诱发电位(ssVEP)和眼动追踪(ET)的混合型并行脑机接口系统的融合方法与指令输出策略开展研究,10名受试者参与了离线验证实验。结果表明:ssVEP与ET融合结果优于使用单一模态信号脑机接口的分类正确率与信息传输速率,在1 s数据长度下,其离线平均分类正确率与信息传输速率分别为99.02%和156.04 bit/min,高于单独ssVEP的85.70%和122.82 bit/min以及单独ET的94.45%和143.49 bit/min。混合型脑机接口系统有助于其在高可靠性系统的推广应用。

In the current single brain-computer interface,the instruction classification accuracy and the information transmission rate are low.To solve this problem,a parallel EEG-ET acquisition sys-tem hardware was built and the fusion method and instruction output strategy of hybrid parallel brain-computer interface based on steady-state visual evoked potential(ssVEP)and eye tracking(ET)were studied.A total of 10 subjects participated in the offline verification experiment.The results showed that the fusion results of ssVEP and ET were better than a single-modal signal brain-comput-er interface in the classification accuracy and information transmission rate.Under 1s data length,the offline average classification accuracy and information transmission rate were 99.02%and 156.04 bit/min,respectively,which were higher than 85.70%and 122.82 bit/min of ssVEP or 94.45%and 143.49 bit/min of ET.The hybrid brain-computer interface system is promising in high-reliability system applications.