STREAM: Self-Supervised Task-Responsive EEG Architecture for Mental-State Estimation

Arian Khorasani (), Thaddé Rolon-Merette (), Alexander Karran (), Pierre-Majorique Léger () and Théophile Demazure ()
Additional contact information
Arian Khorasani: HEC Montréal, Department of Information Technologies
Thaddé Rolon-Merette: HEC Montréal, Department of Information Technologies
Alexander Karran: HEC Montréal, Department of Information Technologies
Pierre-Majorique Léger: HEC Montréal, Department of Information Technologies
Théophile Demazure: HEC Montréal, Department of Information Technologies

A chapter in Information Systems and Neuroscience, 2025, pp 65-73 from Springer

Abstract: Abstract In NeuroIS, cognitive state inference provides rich insight into users’ cognitive experiences during information technology use. However, inferences drawn from electroencephalography (EEG) - one of the most common methods used in NeuroIS - face critical challenges in real-world applications due to label scarcity and cross-task variability. This work introduces a self-supervised learning framework that combines masked prediction and contrastive learning to learn robust EEG representations from unlabeled data. Pre-trained on both controlled (N-back) and naturalistic (MATB-II) tasks, our approach employs hybrid fine-tuning, leveraging full labels from N-back and sparse MATB-II annotations to enhance cross-task generalization. Evaluations demonstrate a 68.2% classification accuracy on MATB-II. This work establishes a framework for label-scarce EEG analysis in NeuroIS, advancing mental state measurement in ecologically valid settings where annotations are limited.

Keywords: EEG; Mental workload; N-back; MATB-II; NeuroIS; Self-supervised learning (SSL) (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnichp:978-3-032-00815-2_6

Ordering information: This item can be ordered from
http://www.springer.com/9783032008152

DOI: 10.1007/978-3-032-00815-2_6

Access Statistics for this chapter

More chapters in Lecture Notes in Information Systems and Organization from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().