Research Of Algorithm Of BCI Based On The Imaginary Left And Right Hand Movement

Brain-Computer Interface(BCI) is a novel human-computer interface. It is a system that transfers brain information and realizes control by using the computer or other electrical devices to analyze the brain activities under specific environment and conditions, without depending on brain`s normal output channels of peripheral nerves and muscles. Thus, the research on BCI is significant to rehabilitation engineering and the development of new communication and control approaches. It has been drawing more and more attention of scientists from the fields of brain cognition research, rehabilitation engineering, biomedical engineering, automatic human- machine control, and so on.First,we give a basic introduction of the structure of brain and brain electric ity, which is the object of our research. Then, oriented to the left vs. right hand motor imagery based on BCI, offline research on the algorithms of feature extraction and feature classification was carried out for the small number of samples from the public data sets of 2003 International BCI Algorithm Contests. At the beginning, feature bands were selected by power spectra analysis of the EEGs from channel C3 and C4 based on the properties of ERD/ERS. Then, non-parameter features were extracted based on the AR model and the bispectrum. In the end, using the way based on spectrum, AR model and bispectrum to extract the features of the signal, and classify the features by using the feature classification algorithms of LDA, SVM and BP.In the paper, the main work is the study of basic algorithm of BCI, which includes feature extraction and feature classification. These works provide the theoretical support for the real-time on-line BCI system. At the same time, a comparison is given between the results of different feature classification algorithms, which can be regarded as the evaluation of each algorithm. The aim of our work is to find the feat ure classification algorithm which can achieve the highest accuracy. Though, we have not made it, but useful experiences have been gained from the work.