Decoding Cognitive Processes in Arithmetic Tasks: An EEG-Based Convolutional Neural Network Model

Nikola Petrović, Lemana Spahić, Sanja Mandić, Platon Sovilj

Abstract

– In this study, we introduce a novel system, developed in Python, for classifying cognitive processes based on EEG signals. The system employs a Convolutional Neural Network (CNN) trained on a dataset comprising 4-minute EEG recordings from 30 subjects. Each EEG sample processed for CNN input is 0.5 seconds long and is transformed into EEG power levels for each channel. The primary achievement of this research is the successful use of the CNN to classify whether a subject is performing a cognitive task well or poorly. The system's performance has been validated by experts in cognitive neuroscience and psychology, and its results have been benchmarked against state-ofthe-art studies in the field. This work represents a significant contribution to the field of EEG-based cognitive process classification, demonstrating the effective integration of machine learning techniques and neuroscience data.

Keywords

Decoding Cognitive Processes, Arithmetic Tasks, EEG, Convolutional Neural Network Model

Download

IMEKO-TC4-2023-36.pdf

DOI

10.21014/tc4-2023.36

IMEKO TC

TC4 - Measurement of Electrical Quantities

Back to the proceedings