Brain-Computer Interface (BCI) is a kind of direct way of information interchange between human brain and the computer or the other electronic equipment. It is a kind of brand-new information interchange system not relying on the normal output channel of brain. BCI is an inevitable result with the development of electronic and computer technology. There are two ways incloding in the research of BCI. One is the human brain that produces and controls the thinking activity information measured in BCI system. Another is the BCI system which identifies the thinking activity information and turns into the concrete control operation. Therefore the user's intention can be expressed and the information interchange and controlling can be realized directly by thinking. The cross and integration are needed by multi-disciplinary knowledge for the development of BCI. It involves the fields of neurobiology, psychology, engineering, mathematics, and computer science etc.BCI is different from brain-computer interface with the traditional meaning. The tasks of the information can be carried on and controled with the external world by the brain without relying on the routine output, which opens up a kind of brand-new communication way. The research of BCI offers a kind of new help for the disabled personnel. Scientific meaning of study on the BCI technology is that it can offer the new-type remedying function for people with a normal thinking but losing the function of moving or sport, especially for the paralysed patient losing all control of muscle. This kind of function makes them regain the control of feeling and movement by learning the mode of thinking. So, it is of important theory meaning and practical value for us to study the BCI technology so as to promote the development of rehabilitation medicine.The data were obtained with electrode fixed on scalp in noninvasive mode and the software platform of experiment was built in the research. Based on mode of the brain activity, the experiment design method, analysis theory and disposal technology were studied in this paper. Processing arithmatics of the BOLD mode on the MRI were studied so as to decided the position distribution of the active areas.Because of the existing of noise, it was difficult problem for feature extracting from the differentevent-related signals directly. It is of obvious dominance and practical value that we adopt wavelet theory to detect and denoise signal. Based on individual feature in different tasks, arithmetic classification of the neural network was studied. And the related event classification was discussed according to the mode of problem. Experiment design of potential-related and the research of potential-related physiological mechanism were completed also. The space filters were designed and used for obtaining the feature message from the experiment data. Theory and arithmetic of support vector machine used in BCI system were proposed in the paper. Result of experiment and research shows that technology integrated various different kind of -methods is a very valid method in improving the precision of event classification. |