Who is WithMe? EEG features for attention in a visual task, with auditory and rhythmic support
IntroductionThe study of attention has been pivotal in advancing our comprehension of cognition. The goal of this study is to investigate which EEG data representations or features are most closely linked to attention, and to what extent they can handle the cross-subject variability.MethodsWe explor...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2024.1434444/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549935449735168 |
|---|---|
| author | Renata Turkeš Steven Mortier Jorg De Winne Jorg De Winne Dick Botteldooren Paul Devos Steven Latré Tim Verdonck |
| author_facet | Renata Turkeš Steven Mortier Jorg De Winne Jorg De Winne Dick Botteldooren Paul Devos Steven Latré Tim Verdonck |
| author_sort | Renata Turkeš |
| collection | DOAJ |
| description | IntroductionThe study of attention has been pivotal in advancing our comprehension of cognition. The goal of this study is to investigate which EEG data representations or features are most closely linked to attention, and to what extent they can handle the cross-subject variability.MethodsWe explore the features obtained from the univariate time series from a single EEG channel, such as time domain features and recurrence plots, as well as representations obtained directly from the multivariate time series, such as global field power or functional brain networks. To address the cross-subject variability in EEG data, we also investigate persistent homology features that are robust to different types of noise. The performance of the different EEG representations is evaluated with the Support Vector Machine (SVM) accuracy on the WithMe data derived from a modified digit span experiment, and is benchmarked against baseline EEG-specific models, including a deep learning architecture known for effectively learning task-specific features.ResultsThe raw EEG time series outperform each of the considered data representations, but can fall short in comparison with the black-box deep learning approach that learns the best features.DiscussionThe findings are limited to the WithMe experimental paradigm, highlighting the need for further studies on diverse tasks to provide a more comprehensive understanding of their utility in the analysis of EEG data. |
| format | Article |
| id | doaj-art-79647665bf9e415d8329552a7f493744 |
| institution | Kabale University |
| issn | 1662-453X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj-art-79647665bf9e415d8329552a7f4937442025-01-10T12:24:18ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2025-01-011810.3389/fnins.2024.14344441434444Who is WithMe? EEG features for attention in a visual task, with auditory and rhythmic supportRenata Turkeš0Steven Mortier1Jorg De Winne2Jorg De Winne3Dick Botteldooren4Paul Devos5Steven Latré6Tim Verdonck7Internet Technology and Data Science Lab (IDLab), Department of Computer Science, University of Antwerp— Interuniversity Microelectronics Centre (imec), Antwerp, BelgiumInternet Technology and Data Science Lab (IDLab), Department of Computer Science, University of Antwerp— Interuniversity Microelectronics Centre (imec), Antwerp, BelgiumWireless, Acoustics, Environment & Expert Systems (WAVES), Department of Information Technology, Ghent University, Ghent, BelgiumDepartment of Art, Music and Theater Studies, Institute for Psychoacoustics and Electronic Music, Ghent University, Ghent, BelgiumWireless, Acoustics, Environment & Expert Systems (WAVES), Department of Information Technology, Ghent University, Ghent, BelgiumWireless, Acoustics, Environment & Expert Systems (WAVES), Department of Information Technology, Ghent University, Ghent, BelgiumInternet Technology and Data Science Lab (IDLab), Department of Computer Science, University of Antwerp— Interuniversity Microelectronics Centre (imec), Antwerp, BelgiumDepartment of Mathematics, University of Antwerp—Interuniversity Microelectronics Centre (imec), Antwerp, BelgiumIntroductionThe study of attention has been pivotal in advancing our comprehension of cognition. The goal of this study is to investigate which EEG data representations or features are most closely linked to attention, and to what extent they can handle the cross-subject variability.MethodsWe explore the features obtained from the univariate time series from a single EEG channel, such as time domain features and recurrence plots, as well as representations obtained directly from the multivariate time series, such as global field power or functional brain networks. To address the cross-subject variability in EEG data, we also investigate persistent homology features that are robust to different types of noise. The performance of the different EEG representations is evaluated with the Support Vector Machine (SVM) accuracy on the WithMe data derived from a modified digit span experiment, and is benchmarked against baseline EEG-specific models, including a deep learning architecture known for effectively learning task-specific features.ResultsThe raw EEG time series outperform each of the considered data representations, but can fall short in comparison with the black-box deep learning approach that learns the best features.DiscussionThe findings are limited to the WithMe experimental paradigm, highlighting the need for further studies on diverse tasks to provide a more comprehensive understanding of their utility in the analysis of EEG data.https://www.frontiersin.org/articles/10.3389/fnins.2024.1434444/fullEEGvisual attentionauditory supportrhythmic supporttopological data analysis |
| spellingShingle | Renata Turkeš Steven Mortier Jorg De Winne Jorg De Winne Dick Botteldooren Paul Devos Steven Latré Tim Verdonck Who is WithMe? EEG features for attention in a visual task, with auditory and rhythmic support Frontiers in Neuroscience EEG visual attention auditory support rhythmic support topological data analysis |
| title | Who is WithMe? EEG features for attention in a visual task, with auditory and rhythmic support |
| title_full | Who is WithMe? EEG features for attention in a visual task, with auditory and rhythmic support |
| title_fullStr | Who is WithMe? EEG features for attention in a visual task, with auditory and rhythmic support |
| title_full_unstemmed | Who is WithMe? EEG features for attention in a visual task, with auditory and rhythmic support |
| title_short | Who is WithMe? EEG features for attention in a visual task, with auditory and rhythmic support |
| title_sort | who is withme eeg features for attention in a visual task with auditory and rhythmic support |
| topic | EEG visual attention auditory support rhythmic support topological data analysis |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2024.1434444/full |
| work_keys_str_mv | AT renataturkes whoiswithmeeegfeaturesforattentioninavisualtaskwithauditoryandrhythmicsupport AT stevenmortier whoiswithmeeegfeaturesforattentioninavisualtaskwithauditoryandrhythmicsupport AT jorgdewinne whoiswithmeeegfeaturesforattentioninavisualtaskwithauditoryandrhythmicsupport AT jorgdewinne whoiswithmeeegfeaturesforattentioninavisualtaskwithauditoryandrhythmicsupport AT dickbotteldooren whoiswithmeeegfeaturesforattentioninavisualtaskwithauditoryandrhythmicsupport AT pauldevos whoiswithmeeegfeaturesforattentioninavisualtaskwithauditoryandrhythmicsupport AT stevenlatre whoiswithmeeegfeaturesforattentioninavisualtaskwithauditoryandrhythmicsupport AT timverdonck whoiswithmeeegfeaturesforattentioninavisualtaskwithauditoryandrhythmicsupport |