基于独立分量分析的在线脑-机接口系统研究与实现.docx

鉴于独立分量剖析的在线脑-机接口系统研究与实现 安徽大学硕士学位论文Abstract Abstract Brain —Computer interface(BCI)is a new type of Human—Computer interaction technique ．By establishing channels between thehuman brain and externalelectronic devices ，BCI can convert theneural activity of human brainintocontrol commands to complete a predetermined operation ．In the fields such as medical rehabilitation and amusement games，etc．，BCI has a very broad application prospects ．However,there are still some crucial problems related toBCI system implementation need tobesolved， such as the slower response speed of system ，the lower recognition accuracy and SO on．Thus，the researches ofefficient EEGprocessingalgorithms have significant meaning in building online BCI system， In the research of non．invasive BCI，independent component analysis(ICA)has been considered as a promising method for electroencephalogram(EEG) preprocessing and feature enhancement ．However ，SOfar,the most researches about ICA—BCI system are offline analysis based on Matlab platform ． This thesis investigated the ICA—based motor imagery BCI(MIBCI)system ， combining the unsupervised learning characteristics of ICA and Event-Related Desynchronization(ERD)effect induced by motor imageries ，a simple andpractical calculation method of ICA·-based spatial filter and the discriminate ．criterion of three ．class motor imageries were constructed 。Onthis basis ，the online ICA—M1BCI experimental system were implemented based on NeuroScan EEGamplifier and VC++platform ．Themain contentS of the dissertation are as following ： 1．TheEvent-Related  Desynchronization／Synchronization(ERD／ERS) phenomenarelated tOmotor imagery were analyzed intime ／frequency ／spatial domain．The typical MI—EEGfeatureextraction andpaaem classification algorithms weredescribed． 2．Thebasic model of ICA andits feasibility for EEG processing were introduced ，some adjustments on extended infomax ICA algorithm were achieved by III 万方数据 安徽大学硕士学位论文 鉴于独立分量剖析的在线脑 -机接口系统研究与实 现 C++programming l