Classification of electroencephalogram signals based on cursor movement imagery

Brain computer interface technology comes at the beginning of the popular study subject for scientist that of excite all of humanity. By means of that technology it is allowed to control electronic devices for paralyzed or partial paralysis humans to make their lives easier. In literature there have been many cursor movement imagery studies based on electroencephalogram (EEG) signals. However, the obtained results are not satisfied in terms of the classification accuracy, because of EEG signals are regularly contaminated by various electromagnetic waves and change person to person even day by day. In this work we propose fast and accurate classification methods for classifying of up/down/right/left computer cursor movement imagery EEG data. With proposed features we achieved a classification accuracy of 67.11 % on the test data.