Kalman filter parameters as a new EEG feature vector for BCI applications

With recent advances in signal processing and biomedical instrumentation, EEG¹ signals can be used as a new communication channel between human and computers. Implementation of this channel is possible by recording and analyzing brain waves. Such a system translates human thoughts for a computer thus it is called a “Brain Computer Interface” or BCI In this paper, a new feature vector for each EEG channel is introduced using the Kalman filter. This feature vector has equal or in some cases, better performance than the other commonly used features. Different classifiers were used to classify EEG signals using the new features and the results are compared.