摘要
设计一个基于稳态视觉诱发电位(Steady-State Visual Evoked Potential,SSVEP)的嵌入式中文输入系统。使用便携式干电极脑电帽,采用多级刺激-意图映射方案,将有限的意图识别频率分别映射在各级。利用高精度计时器与底层图形绘制结合的软件方法,实现高精度刺激闪烁,并使用典型相关性分析算法处理脑电信号。测试结果表明,该系统产生的视觉刺激准确可靠,可以准确诱发SSVEP信号,且最长可连续使用约8小时,输入速率也有所提高,满足残障人士较长时间的中文沟通交流需求。
An embedded Chinese input system based on steady-state visual evoked potential(SSVEP)was designed.The system uses a portable dry-electrode electroencephalogram(EEG)cap and adopts a multi-level stimulus-intent mapping scheme to map the limited frequency of intention recognition at each level.Using a software method that combines high-precision timers with underlying graphic rendering,high-precision stimulus flickering is achieved,and canonical correlation analysis algorithms are used to process EEG signals.Experiments show that the visual stimuli generated by the system are accurate and reliable,can accurately induce SSVEP signals,and can be used continuously for about 8 hours.It can meet the long-term Chinese communication needs of the disabled.
作者
王忠民
刘攀岩
WANG Zhongmin;LIU Panyan(School of Computer Science and Technology,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;Xi’an Key Laboratory of Big Data and Intelligent Computing,Xi’an University of Posts and Telecommunications,Xi’an 710121,China)
出处
《西安邮电大学学报》
2022年第4期74-79,共6页
Journal of Xi’an University of Posts and Telecommunications
基金
国家自然科学基金项目(61373116)
国家自然科学基金项目(62002287)
国家自然科学基金项目(2022SF-037)。
关键词
脑机接口
稳态视觉诱发电位
典型相关性分析算法
嵌入式系统
多级刺激-意图映射
brain-computer interface
steady-state visual evoked potentials
canonical correlation analysis algorithms
embedded systems
multilevel stimulus-intent mapping