Non-invasive EEG based Brain Computer Interface (BCI) systems have been an interesting research area for many fields. However most of the research done on this subject is synchronous, therefore the state of mind of the user is not similar to its natural behaviour. Considering to provide possible experience in practical applications, self-paced BCI systems started gaining popularity in recent years. However, there are certain challenges yet to be addressed when following this method. Out of the research done on self-paced BCI systems most of them are focused on motor-imagery control whereas research on nonmotor imagery mental tasks is limited. In this research, we analyse the possibility of using the techniques used in the motorimagery method for non-motor imagery mental tasks to be fed into virtual object controlling applications.
In this research we tested different artifact removal methods such as Independent Component Analysis (ICA), filtration methods, and wavelet transformation with threshold. Feature extraction was done using signals representations such as fast Fourier transformation, wavelet transformation and statistical representation of EEG data. Their ability to perform in realtime manner and their information resolution were obtained using different methods. For classification we used Random Forest, Quadratic Discriminant Analysis (QDA), KNearest Neighbour Algorithm (KNN), Support Vector Machine (SVM) and CatBoost. According to the results obtained in this research, we present a comparison between the results of different approaches that were tested out.