Classification of Electroencephalograms during Mathematical Calculations Using Deep Learning

TL;DR

This study employs deep learning techniques to classify EEG signals during mathematical calculations, achieving high accuracy and providing insights into brain activity during cognitive tasks.

Contribution

Introduces a novel approach combining entropy features with RNN-based classifiers for EEG classification during math tasks.

Findings

Achieved 99.72% accuracy with ConvLSTM using entropy features.

Entropy features significantly improve classification performance.

Demonstrates effectiveness of deep learning in BCI applications.

Abstract

Classifying Electroencephalogram(EEG) signals helps in understanding Brain-Computer Interface (BCI). EEG signals are vital in studying how the human mind functions. In this paper, we have used an Arithmetic Calculation dataset consisting of Before Calculation Signals (BCS) and During Calculation Signals (DCS). The dataset consisted of 36 participants. In order to understand the functioning of neurons in the brain, we classified BCS vs DCS. For this classification, we extracted various features such as Mutual Information (MI), Phase Locking Value (PLV), and Entropy namely Permutation entropy, Spectral entropy, Singular value decomposition entropy, Approximate entropy, Sample entropy. The classification of these features was done using RNN-based classifiers such as LSTM, BLSTM, ConvLSTM, and CNN-LSTM. The model achieved an accuracy of 99.72% when entropy was used as a feature and ConvLSTM as a classifier.