脑-机接口中空域滤波技术现状与进展

发布时间：2018-01-19 18:18

本文关键词： 脑-机接口脑电运动想象独立分量分析共同空间模式　出处：《安徽大学学报(自然科学版)》2017年02期 　论文类型：期刊论文

【摘要】：作为一种特殊的人-机交互模式,脑-机接口(brain-computer interface,简称BCI)技术已成为当前脑科学和智能信息处理领域的研究热点.其中,基于头皮脑电(electroencephalography,简称EEG)的BCI(EEGBCI)技术因具有良好的安全性和可操作性,吸引了研究者的广泛关注.但头皮EEG非常有限的空间分辨率和易受干扰等特性,很大程度上限制了EEG-BCI技术的实用化进程.因此,EEG信号处理和模式识别新方法研究已成为BCI领域的一个关键问题.在现有的信号处理方法中,空域滤波技术在EEG伪迹消除和任务相关神经活动获取方面表现出了较明显的优势,近年来在EEG-BCI系统实现研究中得到了广泛应用.论文以运动想象BCI(motor imagery BCI,简称MIBCI)为应用背景,对独立分量分析(independent component analysis,简称ICA)和共同空间模式(common spatial pattern,简称CSP)两种代表性空域滤波方法的原理及其性能进行介绍、分析和比较,总结出两种方法各自的优势和不足,并给出了改进思路.同时指出,ICA空域滤波方法在运动想象脑-机接口系统实现中更具应用潜力.
[Abstract]:As a special human-computer interaction mode, the brain-computer interface is brain-computer interface. BCI technology has become a hot topic in the field of brain science and intelligent information processing, among which electroencephalography is based on scalp electroencephalography. Because of its good security and maneuverability, the technology of BCI / EEGBCI is short for EGI. However, the very limited spatial resolution and easily disturbed characteristics of scalp EEG, to a large extent, limit the practical process of EEG-BCI technology. The research of EEG signal processing and new pattern recognition methods has become a key problem in the field of BCI. Spatial filtering technology has obvious advantages in EEG artifact elimination and task related neural activity acquisition. In recent years, it has been widely used in the research of EEG-BCI system implementation. The background of this paper is BCI(motor imagery BCI (Motion Imagination). Independent component analysis for independent component analysis. The principle and performance of two typical spatial filtering methods, I. e., ICA) and common spatial pattern (CSP), are introduced in this paper. Through the analysis and comparison, the advantages and disadvantages of the two methods are summarized, and the improvement ideas are given. At the same time, it is pointed out that the ICA spatial filtering method has more application potential in the realization of the brain-computer interface system of motion imagination.
【作者单位】：安徽大学计算智能与信号处理教育部重点实验室;安徽大学计算机科学与技术学院;
【基金】：国家自然科学基金资助项目(61271352) 安徽省自然科学基金资助项目(KJ2016A043)
【分类号】：R318;TN713
【正文快照】： 脑-机接口(brain-computer interface,简称BCI)是一种特殊的人-机交互模式,该项研究的初衷在于为运动功能损伤或肢体残疾群体提供一个不依赖周围神经和肌肉的人-机交互通路,以实现大脑对外部设备的直接控制[1].随着脑神经科学和信息技术的进步,BCI应用领域得到了很大扩展,它不

【相似文献】