In this report we propose an approach based on artificial neural networks for the classification and recognitionof various states of the human brain associated with the spatial perception of ambiguous images. Based onthe developed numerical methodology and analysis of the experimental multi-channel EEG data, we create andoptimize an artificial neural network to ensure the accuracy of the classification of EEG states of the brainin visual perception close to 100%. Different interpretations of ambiguous images produce different oscillatorypatterns in the EEG of a person with similar characteristics for each interpretation.
展开▼