Electrode Clustering and Bandpass Analysis of EEG Data for Gaze Estimation

TL;DR

This paper validates EEG-based gaze estimation and shows that reducing electrodes minimally impacts performance, highlighting cost-effective approaches and key EEG features for eye tracking.

Contribution

It demonstrates that high-density EEG caps are unnecessary for gaze estimation and identifies critical electrode clusters and frequencies affecting model accuracy.

Findings

Reduced electrode count maintains performance with slight accuracy loss

Key electrode clusters significantly influence gaze estimation

Certain EEG frequencies are more important for eye tracking

Abstract

In this study, we validate the findings of previously published papers, showing the feasibility of an Electroencephalography (EEG) based gaze estimation. Moreover, we extend previous research by demonstrating that with only a slight drop in model performance, we can significantly reduce the number of electrodes, indicating that a high-density, expensive EEG cap is not necessary for the purposes of EEG-based eye tracking. Using data-driven approaches, we establish which electrode clusters impact gaze estimation and how the different types of EEG data preprocessing affect the models' performance. Finally, we also inspect which recorded frequencies are most important for the defined tasks.