Electrode Clustering and Bandpass Analysis of EEG Data for Gaze Estimation

Ard Kastrati, Martyna Beata Plomecka, Joël Küchler, Nicolas Langer, Roger Wattenhofer
Proceedings of The 1st Gaze Meets ML workshop, PMLR 210:50-65, 2023.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v210-kastrati23a, title = {Electrode Clustering and Bandpass Analysis of EEG Data for Gaze Estimation}, author = {Kastrati, Ard and Plomecka, Martyna Beata and K{\"u}chler, Jo{\"e}l and Langer, Nicolas and Wattenhofer, Roger}, booktitle = {Proceedings of The 1st Gaze Meets ML workshop}, pages = {50--65}, year = {2023}, editor = {Lourentzou, Ismini and Wu, Joy and Kashyap, Satyananda and Karargyris, Alexandros and Celi, Leo Anthony and Kawas, Ban and Talathi, Sachin}, volume = {210}, series = {Proceedings of Machine Learning Research}, month = {03 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v210/kastrati23a/kastrati23a.pdf}, url = {https://proceedings.mlr.press/v210/kastrati23a.html}, 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.} }
Endnote
%0 Conference Paper %T Electrode Clustering and Bandpass Analysis of EEG Data for Gaze Estimation %A Ard Kastrati %A Martyna Beata Plomecka %A Joël Küchler %A Nicolas Langer %A Roger Wattenhofer %B Proceedings of The 1st Gaze Meets ML workshop %C Proceedings of Machine Learning Research %D 2023 %E Ismini Lourentzou %E Joy Wu %E Satyananda Kashyap %E Alexandros Karargyris %E Leo Anthony Celi %E Ban Kawas %E Sachin Talathi %F pmlr-v210-kastrati23a %I PMLR %P 50--65 %U https://proceedings.mlr.press/v210/kastrati23a.html %V 210 %X 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.
APA
Kastrati, A., Plomecka, M.B., Küchler, J., Langer, N. & Wattenhofer, R.. (2023). Electrode Clustering and Bandpass Analysis of EEG Data for Gaze Estimation. Proceedings of The 1st Gaze Meets ML workshop, in Proceedings of Machine Learning Research 210:50-65 Available from https://proceedings.mlr.press/v210/kastrati23a.html.

Related Material