Could we Predict Flow from Ear-EEG?

Advancements in wearable EEG could provide valuable foundations for studying flow experiences in everyday life. In this study, we report initial findings on using unobtrusive, comfortable around-the-ear EEG electrodes (cEEGrids) to monitor flow levels. Tree-based regression models show that flow rep...

Full description

Saved in:
Bibliographic Details
Published in2022 10th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) pp. 1 - 6
Main Authors Knierim, Michael Thomas, Bartholomeyczik, Karen, Nieken, Petra, Weinhardt, Christof
Format Conference Proceeding
LanguageEnglish
Published IEEE 18.10.2022
Subjects
Biomedical monitoring
Brain modeling
cEEGrids
Ear EEG
Electrodes
Electroencephalography
Flow experience
Machine Learning
Mental workload
Predictive models
Real-time systems
Reliability
XGBoost
Online AccessGet full text

Cover

More Information
Summary:Advancements in wearable EEG could provide valuable foundations for studying flow experiences in everyday life. In this study, we report initial findings on using unobtrusive, comfortable around-the-ear EEG electrodes (cEEGrids) to monitor flow levels. Tree-based regression models show that flow reports across three different tasks can be predicted with a mean absolute error (MAE) of 11% across study participants. These results represent a potential starting point for further research with cEEGrids on the momentary capturing of flow in everyday life. Related limitations and propositions are discussed.
DOI:10.1109/ACIIW57231.2022.10086037