On the Task of Dividing EEG Data by Brain Zones for Application in Robot Control

The study discussed in this paper contributes to the extensive interdisciplinary research dedicated to developing a method for controlling robots using human bioelectrical signals. The focus of this research is on investigating the signals obtained through electroencephalography (EEG), assessing their representativeness, and exploring the potential for clustering these signals. A crucial aspect examined is the hypothesis that signals originating from different regions of the brain can be effectively separated and accurately identified. The paper presents the outcomes of an experiment involving the induction of stable visual evoked potentials in human subjects, followed by the creation of a practical database based on these findings. The proposed approach involves extracting significant features from the EEG signal through the application of machine learning methods. The efficiency and practicality of the computational data obtained are thoroughly evaluated. The primary conclusions are formulated, and the hypothesis that each brain channel exhibits distinct waves characteristic of specific brain regions is validated.