EEG-based video identification using graph signal modeling and graph convolutional neural network

TL;DR

This paper introduces a novel graph signal-based deep learning approach utilizing graph convolutional neural networks for EEG data, significantly improving video identification accuracy from EEG responses.

Contribution

It presents new methods for representing EEG data as graph signals and applies graph CNNs to enhance EEG-based video identification performance.

Findings

Proposed graph signal representation improves EEG data analysis.

Graph CNNs outperform existing methods in video identification accuracy.

Effective schemes for EEG graph signal representation are discussed.

Abstract

This paper proposes a novel graph signal-based deep learning method for electroencephalography (EEG) and its application to EEG-based video identification. We present new methods to effectively represent EEG data as signals on graphs, and learn them using graph convolutional neural networks. Experimental results for video identification using EEG responses obtained while watching videos show the effectiveness of the proposed approach in comparison to existing methods. Effective schemes for graph signal representation of EEG are also discussed.