论文部分内容阅读
提出一种通过脑电波来识别放松状态以及乘法作业状态从而实现脑机接口的新方法。利用脑电仪记录受测者放松状态以及乘法作业时的大脑左右半球枕叶部的脑电信号,采用Welch法分别估计出这2个部位8Hz～10Hz、1Hz～13Hz、14Hz～30Hz 3个频段的功率谱,以各个功率谱平均值和2Hz～30Hz频段功率谱平均值的比值作为分类特征,采用支持向量机的方法建立了分类器,从而实现了脑机接口。4个受测者的实验结果表明识别准确率都大于94.44%,最高为98.89%。由于只采用了2个采集点,因此如果采用某种编码方式,该脑机接口技术就可更加方便地用于写字、控制轮椅等方面。
A new method of brain-computer interface is proposed by using brain waves to identify relaxed states and multiplication jobs. The Echocardiograph was used to record the EEG signals of both the left and right hemispheric occipital lobe of the brain in the relaxation state of the test subjects and the frequency of 8Hz ~ 10Hz, 1Hz ~ 13Hz, 14Hz ~ 30Hz by Welch method , The power spectrum of each power spectrum and the average power spectrum of 2Hz ~ 30Hz frequency band as a classification feature, the use of support vector machine method to establish a classifier, so as to achieve the brain-computer interface. The experimental results of 4 subjects showed that the recognition accuracy was more than 94.44% and the highest was 98.89%. Since only two acquisition points are used, the BCI technology can be more easily used for writing, controlling wheelchairs, etc. with some encoding.