探讨通道对视觉诱发电位单次提取精度的影响  

Effect to Channel in Single-Trial Visual Evoked Potential Estimation

作　　者：肖贵贤[1] 严伟[1] 官金安[2] 

机构地区：[1]黄石理工学院,黄石435003 [2]中南民族大学生物医学工程研究所,武汉430074

出　　处：《中国医疗器械信息》2010年第4期49-51,共3页China Medical Device Information

摘　　要：采用"模拟自然阅读"诱发电位作为脑-机接口通信载体,结合小波变换和误差逆传播(Error Back Propagation,即BP)神经网络对视觉诱发脑电信号(VEP)进行分类以产生脑机接口控制信号。将被试者4个通道记录到的脑电信号分别作为特征,信号时程都为300ms,时段分别取100ms～400ms、200ms～500ms和300ms～600ms。试验结果表明四个单通道都达到较好的分类效果,有利于产生脑机接口控制信号。Adopting the＂Imitating-natural-reading＂elicited potentials as carriers between brain and computer.The classification of visual evoked potential（VEP） with wavelet transform and BP neural network was used to obtain brain-computer interface （BCI） control signal. Taking the signals from the four EEG recordings as features and setting the time length of signal in a trial as 300ms, the classification rates were tested on average with three time intervals,namely, 100ms-400ms, 200ms-500ms, and 300ms-600ms. The test results showed that four single-channel up to a good classification results.It is useful to produce BCI control signal.

关 键 词：视觉诱发电位(VEP) 脑机接口 小波变换 BP神经网络 

分 类 号：R318[医药卫生—生物医学工程] TP18[医药卫生—基础医学]