Identification of real and imaginary movements in eeg using machine learning models

Abstract

The neural activity of the brain may be observed by means of an electroencephalogram (EEG) whose analysis and/or interpretation may lead to the recognition of human activities and behaviors. However, on imagined body movements the brain produces the same EEG patterns as the action performed. This study aims to differentiate real movements from imagined ones, through EEG signals. Three different models; Support Vector Machine, Logistic Regression, and K-Nearest neighbour were implemented to classify these events. The preliminary results, obtained from 15 participants, revealed that the Logistic Regression was the best classifier into the proposed model with accuracy rates varying from 36.8 to 90%. Finally, complementary studies should be addressed to optimize not only the accuracy but also to assure uniform accuracy among the different participants.