机构地区: 东北大学机械工程与自动化学院
出 处: 《系统仿真学报》 2007年第19期4581-4582,4598,共3页
摘 要: 脑-机接口是一种不依赖于正常的由外围神经和肌肉组成的输出通路的通讯系统。利用功率谱和神经网络对不同意识任务的脑电信号进行分类。首先对脑电信号进行预处理和基于MUSIC算法的功率谱,提取脑电信号功率谱值作为特征,然后利用LVQ网络对两类不同意识任务进行分类。仿真试验表明,该方法取得了很好的分类效果,而且分类速度非常快。 The Brain-Computer Interface (BCI) is a communication system that does not depend on the brain's normal output pathways of peripheral nerves and muscles. EEG signals were classified during different mental tasks using Power Spectral Density (PSD) and artificial neural network. The EEG signal was preprocessed and the PSD was computed based on Multiple Signal Classification (MUSIC) algorithm, and the features were extracted from the PSI) of 6-13 Hz. Learning Vector Quantization (LVQ) neural network was used to classify two different mental tasks. From the simulation of the experiment, a good result was got, and this method is very quick.
领 域: [自动化与计算机技术] [自动化与计算机技术]