Classification of EEG signals using different feature extraction techniques for mental-task BCI

The use of Electroencephalogram (EEG) or “brain waves” for human-computer interaction is a new and challenging field that has gained momentum in the past few years. If several mental states can be reliably distinguished by recognizing patterns in EEG, then a paralyzed person could communicate to a device like a wheelchair by composing sequences of these mental states. In this research, EEG from one subject who performed three mental tasks have been classified using Radial Basis Function (RBF) Support Vector Machines (SVM) to control overfitting. A method for EEG preprocessing based on Independent Component Analysis (ICA) was proposed and three different feature extraction techniques were compared: Parametric Autoregressive (AR) modeling, AR spectral analysis and power differences between four frequency bands. The best classification accuracy was approximately 70% using the parametric AR model representation with almost 5 % improvement of accuracy over unprocessed data.