Mental Task Classification Using Electroencephalogram Signal

TL;DR

This study explores EEG-based mental task classification using CNN, LSTM, GRU, and introduces a novel mixed LSTM-CNN decoder model, achieving improved accuracy and robustness over traditional models.

Contribution

The paper proposes a new mixed LSTM model with a CNN decoder for EEG classification, demonstrating superior accuracy and robustness compared to existing CNN and LSTM models.

Findings

Mixed LSTM-CNN model achieves 70% test accuracy.

CNN hyperparameter tuning yields 62% test accuracy.

Stacked LSTM and GRU models reach 55% and 51% accuracy.

Abstract

This paper studies the classification problem on electroencephalogram (EEG) data of mental tasks, using standard architecture of three-layer CNN, stacked LSTM, stacked GRU. We further propose a novel classifier - a mixed LSTM model with a CNN decoder. A hyperparameter optimization on CNN shows validation accuracy of 72% and testing accuracy of 62%. The stacked LSTM and GRU models with FFT preprocessing and downsampling on data achieve 55% and 51% testing accuracy respectively. As for the mixed LSTM model with CNN decoder, validation accuracy of 75% and testing accuracy of 70% are obtained. We believe the mixed model is more robust and accurate than both CNN and LSTM individually, by using the CNN layer as a decoder for following LSTM layers. The code is completed in the framework of Pytorch and Keras. Results and code can be found at https://github.com/theyou21/BigProject.