Principal Investigator: Assistant Professor Mads Jochumsen
Center for Sensory-Motor Interaction (SMI) – Department of Health Science and Technology – Aalborg University (AAU)
Our work concerns Brain Computer Interfaces, translating EEG into control signals for a variety of assistive devices. EEG is very dense data and can be analyzed in many ways. Thus, HPC is in high demand for explorative EEG studies. ABACUS 2.0 enabled us to extract and evaluate a large number features of the EEG recorded during internal speech, and thus reveal patterns that enabled a Random Forest algorithm to predict the internally spoken words. The preliminary results show a >70 % classification accuracy in a 6-class problem.