基于运动想象与稳态视觉诱发电位的混合脑机接口系统研究

发布时间：2018-04-03 23:07

本文选题：脑-机接口　切入点：运动想象　出处：《昆明理工大学》2017年硕士论文

【摘要】：脑-机接口(Brain-Computer Interaction,BCI)是一种直接利用脑电信号,不依赖于正常的输出通道(外周神经和肌肉),实现人脑与外部环境通讯和控制的技术。脑-机接口使脑科学、信息科学与控制科学交叉跨学科研究,已成为国际重大前沿突破点。这一技术不仅可望战略性地用于国防军事目的,也可望为严重运动残疾患者提供一种新的通信和控制通道,从而改善他们的生活质量。本文主要研究基于运动想象(Motor Imagery,MI)与稳态视觉诱发电位(Steady State Visual Evoked Potentials,SSVEP)脑电的混合脑-机接口系统。分别设计了基于运动想象脑电的异步BCI系统、基于SSVEP的BCI系统以及基于运动想象与SSVEP的混合BCI系统。对于基于运动想象脑电的异步BCI系统,针对运动想象脑电信号,研究对比了不同的预处理、特征提取和模式识别方法,探讨了基于三通道左右手运动想象脑电的异步BCI系统的有效性。对于基于SSVEP的BCI系统,采用普遍认可典型相关分析(Canonical Correlation Analysis,CCA)方法,研究了不同刺激范式对模式识别的影响,并进一步设计系统进行了控制机器人方向和速度的研究,可望为基于SSVEP的脑-机交互应用于分级或精细控制机器人方向和速度提供思路,并为直接脑控机器人技术推向实际应用打下一定的基础。对于基于运动想象与SSVEP的混合BCI系统,设计了针对运动想象与SSVEP两种不同模态脑电信号的融合系统,采用串行控制,通过对特定模态脑电信号的分类识别,系统可以自由切换至基于另一种模态的BCI系统。本文可望为多模态脑-机接口系统开发提供一定的启发,并为脑-机接口走向实际应用打下一定的基础。
[Abstract]:Brain-Computer interaction (BCI) is a technique that directly utilizes EEG signals and does not depend on normal output channels (peripheral nerve and muscle) to realize communication and control between human brain and external environment.Brain-Computer Interface (BCI) has become an important breakthrough point in the field of brain science, information science and control science.This technology is expected not only to be strategically used for defense and military purposes, but also to provide a new channel of communication and control for people with severe sports disabilities, thereby improving their quality of life.In this paper, a hybrid brain-computer junction system based on motor imagery MIA and Steady State Visual Evoked potential SSVEP is studied.The asynchronous BCI system based on motor imagination EEG, the BCI system based on SSVEP and the hybrid BCI system based on motion imagination and SSVEP are designed respectively.For the asynchronous BCI system based on motion imagination EEG, different preprocessing, feature extraction and pattern recognition methods are studied and compared.The effectiveness of an asynchronous BCI system based on three-channel left-right-hand motion imagination is discussed.For the BCI system based on SSVEP, the influence of different stimuli paradigm on pattern recognition is studied by using the commonly accepted canonical Correlation Analysis method, and the direction and speed of the robot are further studied by designing the system.It is expected to provide some ideas for the application of brain-computer interaction based on SSVEP in the direction and speed control of hierarchical or fine robot, and lay a foundation for the practical application of direct brain-controlled robot technology.For the hybrid BCI system based on motion imagination and SSVEP, the fusion system of motion imagination and SSVEP is designed. The serial control is used to recognize the special mode EEG signal.The system can freely switch to a BCI system based on another mode.This paper is expected to provide some inspiration for the development of the multimodal brain-computer interface system and lay a foundation for the practical application of the brain-computer interface.
【学位授予单位】：昆明理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：R318;TN911.7;TP242

【相似文献】