EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Decoding study-independent mind-wandering from EEG using convolutional neural networks

Christina Yi Jin iD, Jelmer P Borst, Marieke K van Vugt

Journal of Neural Engineering · 01.04.2023 · 20 (2) · 026024

DOI: 10.1088/1741-2552/acc613 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neural Engineering, online erschienen am 31.03.2023. Verfasst von Christina Yi Jin und 2 weiteren Autor:innen. Beteiligte Einrichtung: Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen 9747AG, The Netherlands. Hauptthemen laut MEDLINE: Electroencephalography, Machine Learning. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective . Mind-wandering is a mental phenomenon where the internal thought process disengages from the external environment periodically. In the current study, we trained EEG classifiers using convolutional neural networks (CNNs) to track mind-wandering across studies. Approach . We transformed the input from raw EEG to band-frequency information (power), single-trial ERP (stERP) patterns, and connectivity matrices between channels (based on inter-site phase clustering). We trained CNN models for each input type from each EEG channel as the input model for the meta-learner. To verify the generalizability, we used leave-N-participant-out cross-validations ( N = 6) and tested the meta-learner on the data from an independent study for across-study predictions. Main results . The current results show limited generalizability across participants and tasks. Nevertheless, our meta-learner trained with the stERPs performed the best among the state-of-the-art neural networks. The mapping of each input model to the output of the meta-learner indicates the importance of each EEG channel. Significance . Our study makes the first attempt to train study-independent mind-wandering classifiers. The results indicate that this remains challenging. The stacking neural network design we used allows an easy inspection of channel importance and feature maps.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyMachine LearningHumansNeural Networks, ComputerMental Processes

Stichwörter der Autor:innen

EEGclassifierconvolutional neural networkgeneralizabilitymachine learningmeta-learnermind-wandering

Autor:innen und Institutionen

  • Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen 9747AG, The Netherlands.
  • Research Center for Augmented Intelligence, Zhejiang Lab, Hangzhou 310000, People's Republic of China.

ORCID-Profile: Christina Yi Jin

Zitieren

APA

Jin, C. Y., Borst, J. P., & van Vugt, M. K. (2023). Decoding study-independent mind-wandering from EEG using convolutional neural networks. Journal of Neural Engineering, 20(2), 026024. https://doi.org/10.1088/1741-2552/acc613

Vancouver

Jin CY, Borst JP, van Vugt MK. Decoding study-independent mind-wandering from EEG using convolutional neural networks. Journal of Neural Engineering. 2023;20(2):026024. doi:10.1088/1741-2552/acc613

BibTeX
@article{Jin2023,
  author = {Jin, Christina Yi and Borst, Jelmer P and van Vugt, Marieke K},
  title = {Decoding study-independent mind-wandering from EEG using convolutional neural networks},
  journal = {Journal of Neural Engineering},
  year = {2023},
  volume = {20},
  number = {2},
  pages = {026024},
  doi = {10.1088/1741-2552/acc613}
}
Kostenlos starten →