Detection of task difficulty from intention level information in the EEG features

In this study, an approach which detects the level of intention in response to the difficulty of the task executed by the subjects in an electroencephalogram (EEG) based brain-computer interface (BCI), is proposed. For this purpose, event related synchronization and desynchronization patterns which occur in the process of lifting different weights by the right hand by executing elbow flexion and extension movements, are classified by the linear discriminant analysis (LDA). Our results show that the varying difficulty of the task can be classified based on the EEG signals. In addition, a correlation analysis between the intention levels detected from EEG and surface electromyogram (sEMG) signals is presented and the detected level of correlation between these two signals supports our previous inference. Determining the level of intention of the patients during the physical rehabilitation treatment, ensures the patients' active participation in their therapy task and increases the effectiveness of the robotic rehabilitation system. Accordingly, the type of intention level detection approach we propose here has the potential to be useful in such physical rehabilitation processes.