Brain Signal Processing Based On Motor Imagery

Brain-Computer Interface (BCI) is a brand-new interface between the human brain and the computer. It's aimed at developing a technical system with extra communication and control channels that do not depend on the brain's normal output pathways of peripheral nerves and muscles. Current interests in BCI development come mainly from the hope that this technology could be a new valuable augmentative communication option for those with severe motor disabilities that prevent them from using conventional augmentative technologies. During these years, the BCI projects that based on the electroencephalogram (EEG) signals have been the key topics.In BCI systems, feature extraction and classification is the crucial work for EEG signals analysing.Our study in this dissertation is mainly about this work. Main research power spectrum analysis, the AR model power spectrum analysis and events related synchronous/synchronization method in the analysis of application to extract the brain signals. Power spectrum estimation using AR model method and events related synchronous/synchronization analysis method of synchronization feature extraction. Then using Mahalanobis distance classifier, Fisher based on the criteria of classifier and improved BP neural network of three different classification method based on AR model power spectrum estimation and events related to the event synchronous/synchronization imagine classification, features and classification accuracy comparing the result. From the Angle of analysis, the classified accuracy for the same kind of general nonlinear characteristics, its classification effect is better than linear method. For comparison, the classifier can only see classification accuracy, its design and difficulty, and training and performance evaluation classification rate is an important index of these factors in actual applications must be considered. For this, two linear classifiers are simple in design, without training, and fast.in classification.