基于傅里叶变换的脑机接口系统实现方法

Implementation method of brain-computer interface system based on Fourier transform

脑机接口系统要求实时的处理速度和较高的准确识别率.在对脑电信号进行幅频分析和相同步分析的基础上,提出一种意识任务识别在线脑机接口系统实现方法.提取谱峰和相同步相干性指数作为反映大脑运动意识任务状态的特征参量,设计基于信息积累的时变线性分类器,对左右手想象意识任务进行识别,获得了满意的结果,最大分类正确率达到90.72%.研究结果表明,谱峰特征是事件相关去同步/同步的一个敏感的量化参数,结合相同步相干性指数能够提供更多反映大脑意识任务状态的信息.该方法采用快速傅里叶变换和线性判别式分析,特征提取和分类算法简单,计算速度快.为在线脑机接口系统的实现提供了新的思路和途径.

Brain-computer interface （BCI） systems require real-time processing speed and higher and more accurate identification rate. An implementation method of on-line BCI systems for identification of mantel tasks was presented on the basis of analysing the amplitude-frequency and phase synchronization of brain＇s electrical signals. Taking the extracted spectral peak and phase synchronization coherency index as the characteristic parameters for expressing the imaginary movements in the brain, a time-variable linear classifier was designed on the basis of informations accumulation for identifying the imaginary mental tasks of left and right hands, so that a satisfactory result was obtained with the maxim accuracy of 90. 72%. The investigation results showed that the characteristics of spectral peak was a sensitive parameter for quantifying the measure of event-related desynchronization/synchronization, and the sptetra peak combined with phase coherency index could provide more information reflecting the state of brain＇s mental tasks. The presented algorithm with fast Fourier transform and linear discriminant analysis for feature extraction and classification was simple and quick-operational, providing a new idea and means to realize the on-line BCI system.