融合眼动追踪和目标动态可调的稳态视觉诱发电位脑机接口系统设计  

A Design of Brain-Computer Interface System for Steady-State Visual Evoked Potential Integrating Eye Movement Tracking and Target Dynamical Adjustment

作　　者：何柳诗 谢俊[1] 于鸿伟 任志远 杨育喆 李敏[1] 徐光华[1] HE Liushi;XIE Jun;YU Hongwei;REN Zhiyuan;YANG Yuzhe;LI Min;XU Guanghua(School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China)

机构地区：[1]西安交通大学机械工程学院,西安710049

出　　处：《西安交通大学学报》2021年第10期87-95,共9页Journal of Xi'an Jiaotong University

基　　金：人因工程重点实验室开放基金资助项目(SYFD061903K)。

摘　　要：针对视觉脑机接口应用过程中,刺激目标数量多且面积小时视觉响应不强,被试者疲劳时难以将注意力集中在同等大小刺激目标上的问题,设计了一种基于眼动追踪和视觉目标动态可调的脑机接口系统。该系统利用TCP/IP传输协议实现眼动信号和脑电信号的同步采集,并将眼动信号以视觉反馈的形式实时呈现在刺激显示界面,即有提示被试者视线落点位置以便集中注意力到目标刺激上的作用,起到控制目标刺激大小的作用。该系统结合了眼动追踪快速高效和稳态视觉诱发电位脑机接口(SSVEP-BCI)频谱稳定、信噪比高等优势,眼动反馈信号快速调控刺激目标增大并吸引被试者注意,以激发更高的脑电响应和提升识别正确率。将无眼动反馈刺激目标动态可变、无眼动反馈刺激目标不变作为对照组进行实验,结果表明:有眼动反馈目标动态可变的脑机接口系统能比无眼动反馈目标动态可变、无眼动反馈目标不变系统在更短的时间窗内达到80%以上的识别正确率,且具有更高的脑电响应幅值;在3 s时间窗内,有眼动反馈目标动态可变的脑机接口系统的平均识别正确率为92.97%,脑电响应幅值为1.824μV,高于平均识别正确率为88.39%及脑电响应幅值为1.379μV的无眼动反馈目标动态可变系统,且高于平均识别正确率为79.48%及脑电响应幅值为0.987μV的无眼动反馈目标不变系统,这表明有眼动反馈且刺激目标动态可调的脑机接口系统具有更好的识别效果且能诱发更高的脑电响应,工作性能更好。In the application of visual brain-computer interface(BCI),a BCI system based on eye movement tracking and dynamic adjustment of visual targets is designed to solve the problems that the visual response is weak when the number of stimulate targets is large and the area is small,and it is difficult for the subjects to focus on specific targets of the same size when they are tired.The system uses TCP/IP transmission protocol to realize the synchronous acquisition of eye movement signals and electroencephalogram(EEG)signals,and presents the eye tracking results in the form of visual feedback on the stimulation display interface in real time.It has the role in controlling the size of the desired target,and promoting the subjects to focus their attention on the desired target efficiently.The system combines the advantages of fast and efficient eye movement tracking and steady-state visual evoked potential BCI with stable EEG spectrum and high signal-to-noise ratio.The rapid regulation of eye tracking feedback stimulates the target to enlarge and attracts the attention of subjects,so as to evoke higher EEG response and improve the recognition accuracy.An experiment is carried out with dynamically variable of non-eye movement feedback stimulation targets and invariable of non-eye movement feedback stimulation targets as a comparison group.The results show that the BCI system with eye movement tracking feedback and dynamic adjustment of visual targets achieves more than 80%recognition accuracy and much higher EEG response amplitude in a short time window length than the system without eye tracking feedback and the system with the constant target size.In the 3 s time window length,the average recognition accuracy and EEG response amplitude of the BCI system with eye tracking based dynamic adjustment of visual targets are 92.97%and 1.824μV,respectively,which are higher than 88.39%and 1.379μV of the BCI system without eye tracking feedback respectively,and higher than 79.48%and 0.987μV of the BCI system with the constant

关 键 词：稳态视觉诱发电位 眼动追踪 脑机接口 视觉反馈 动态可调 

分 类 号：TP23[自动化与计算机技术—检测技术与自动化装置]