P300 Chinese input system based on Bayesian LDA
P300 Chinese input system based on Bayesian LDA
复制标题
DOI：
10.1515/bmt.2010.003
复制
发表时间：
2010-01-01
期刊：
影响因子：
--
通讯作者：
Pfurtscheller, Gert
中科院分区：
文献类型：
--
作者：
Jin, Jing;Allison, Brendan Z.;Pfurtscheller, Gert
脑机接口(BCI)是人类和计算机之间的一种新的通信渠道，它将大脑活动转化为可识别的命令和控制信号。参与活动可在脑电中诱发P300电位。因此，P300已经被用于BC1系统中，用于拼写、控制光标或机器人设备，以及其他大头针。介绍了一种新型的用于汉字通信的P300脑机接口。为了提高分类精度，使用了一种优化算法(粒子群优化算法，PSO)来进行通道选择(即识别最佳电极配置)。通过贝叶斯线性判别分析，离线检验了不同电极配置对分类精度的影响。I-I受试者的离线结果表明，这种新的P300脑-机接口可以有效地进行汉字交流，并且用粒子群算法从电极中提取的特征取得了良好的效果。
A brain-computer interface (BCI) is a new communication channel between humans and Computers that translates brain activity into recognizable command and control signals. Attended events can evoke P300 potentials in the electroencephalogram. Hence, the P300 has been used in BC1 systems to spell, control cursors or robotic devices, and other tacks. This paper introduces a novel P300 BCI to communicate Chinese characters. To improve classification accuracy, an optimization algorithm (particle swarm optimization, PSO) is used for channel selection (i.e., identifying the best electrode configuration). The effects of different electrode configurations on classification accuracy were tested by Bayesian linear discriminant analysis offline. The offline results from I I subjects show that this new P300 BCI can effectively communicate Chinese characters and that the features extracted from the electrodes obtained by PSO yield good performance.