EEG signal cleaning for drowsiness detection

The communication between the brain and external devices can be done with different methods, but at least one EEG signal recorder is needed in order to get the electrical activity of the brain plus an application to perform the processing of the raw data, moreover an algorithm must be developed for the interpretation of the brain activity. In this paper two new adapted algorithms are proposed for EEG signal cleaning and also some basic features will be extracted in order to detect drowsiness. We used physionet database [18] in order to perform these duties. Our contribution in this work is to adapt zero-crossing filter for power supply noise removal and also the usage of the polynomial interpolation to remove the baseline artifact.