Deep Learning-Based Approach for Classification Of Mental Tasks From Electroencephalogram Signals

Abstract

Background and Objective: Electroencephalography (EEG) analysis is an important tool for neuroscience, brain-computer interface studies, and biomedical studies. The primary purpose of Brain-Computer Interface (BCI) studies is to establish communication between disabled individuals, other individuals, and machines with brain signals. Interpreting and classifying the brain's response during different cognitive tasks will contribute to brain-computer interface studies. Therefore, in this study, five cognitive tasks were classified from EEG signals. Material and Methods: In this study, five neuropsychological tests (Öktem Verbal Memory Processes Test, WMS-R Visual Memory Subtest, Digit Span Test, Corsi Block Test, and Stroop Test) were administered to 30 healthy individuals. The tests assess the volunteers' abilities in verbal memory, visual memory, attention, concentration, working memory, and reaction time. The EEG signals were recorded while the tests were administered to the volunteers. The tests were classified using two different deep learning algorithms, 1D Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), from the recorded EEG signals. Results: When the success of the tests was evaluated, classification success was achieved with an accuracy of 88.53% in the CNN deep learning algorithm and 89.80% in the LSTM deep algorithm. Precision, recall, and F1-score values for CNN were calculated at 0.88, 0.87, and 0.87, respectively, while precision, recall, and f1-score values for the LSTM network were obtained at 0.90, 0.89, and 0.89. Conclusion: Following the findings of the present study, five different cognitive tasks were able to be classified with high accuracy from EEG signals using deep learning algorithms.