EEG artifact signals tracking and filtering in real time for command control application

Abstract

Brain machine interface (BMI) is a direct communication pathway between human's brain and an external device. In some researches it is also called Brain-Computer interface (BCI). There are two types of motor BMIs: invasive and non-invasive. Research on non-invasive BMIs started in the 1980s by measuring brain electrical activity over the scalp electroencephalogram (EEG). In this paper, an attempt in made to present initial steps on a non-invasive BMI design based on pattern recognition algorithm method on EEG signals. These artifact signals are converted to command signals to control and steer an external object. The EEG signal is contaminated with numerous artifact signals which make the assembly of usable artifact signal very difficult. With help of MATLAB program, tracking and filtering of artifact signals in real time application is presented as well. © 2011 Springer-Verlag.