Effects of Brain Signal Preprocessing on Visual Object Stimulation

In this paper, we focus on the interpretation of brain signals generated by Visual Evoked Potentials (VEPs) stimulation. For stimulation, videos were created that included three categories of animals. During stimulation, signals were recorded using OpenBCI's EEG acquisition system. The recorded signals were preprocessed by removing the DC offset with different parameter settings. Based on the results, we investigated whether it was possible to recognize if different subjects saw the same category of animals and whether the subject could distinguish between animal categories. The preprocessed EEG signals were compared using the correlation coefficient. Using such an approach, it would be possible to create a system for nonverbal human-machine communication based on the semantic analysis of images, context and transformer technology widely used in LLM (Large Language Models).