Brain signal reference concept using cross correlation based for brain computer interface

The sub system for EEG based brain computer interface system are feature extraction and classification. Translation from brain signal that contain a human intention into computer´s command or message should be accomplished with good feature extraction nor classification. One of the methods for analyzing brain signal in feature extraction process is using band power measurement from few or many EEG channels. Recalibration or daily calibration was needed in using brain computer interface instrument. In order to make the feature extraction more reliable, the proposed method is using brain signal reference. To develop brain signal reference, sampling method taken from brain signal when human intention occur. The next feature extraction will analyze whether the signal is similar with signal reference or not. Feature extraction will uses cross correlation method to measure the similarity. Based on the hypothesis that brain will produce the similar signal in the same intention, the brain signal reference concept is the method can be used for feature extraction process. It is also should be considered the level of similarity which it will transfer to classification process in estimating the intention. It is feasible using brain signal reference concept based on cross correlation method.