EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Cross-Dataset Mental Workload Detection Using Electrodermal Activity and Domain Adaptation

Luis Sigcha, Eduarda Pereira, Luigi Borzì, Diego Gachet, Paulo Cardoso, Nélson Costa

Applied Sciences · 08.05.2026 · 16 (10) · 4673

DOI: 10.3390/app16104673 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 08.05.2026. Verfasst von Luis Sigcha und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FCT – Fundação para a Ciência e Tecnologia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mental workload assessment using physiological signals has gained increasing attention for applications in human–computer interaction and occupational monitoring. Among these signals, electrodermal activity (EDA) is widely recognised as a reliable indicator of sympathetic activation associated with cognitive effort. However, most existing machine learning- based approaches are evaluated within a single dataset, limiting their generalisability across different populations and experimental conditions. This study investigates the cross-dataset performance of machine learning models for mental workload detection using EDA features. Two independent datasets were employed, and a cross-dataset evaluation framework was adopted to simulate realistic deployment scenarios under domain shift. Three classifiers (Random Forest, XGBoost, and Support Vector Classifier (SVC)) were evaluated, together with two domain adaptation techniques: Correlation Alignment (CORAL) and Subspace Alignment (SA). The results show that model performance is strongly dependent on the direction of transfer, with a notable performance drop when generalising across datasets. Domain adaptation improved performance in several configurations, particularly for SVC with CORAL, achieving the best overall F1-score (0.815). However, improvements were not consistent across all models and target domains. Overall, this study highlights the challenges of cross-dataset generalisation in EDA-based workload detection and demonstrates the potential, yet limited robustness, of domain adaptation techniques in mitigating distribution shifts.

Förderung

  • FCT – Fundação para a Ciência e Tecnologia

Zitieren

APA

Sigcha, L., Pereira, E., Borzì, L., Gachet, D., Cardoso, P., & Costa, N. (2026). Enhancing Cross-Dataset Mental Workload Detection Using Electrodermal Activity and Domain Adaptation. Applied Sciences, 16(10), 4673. https://doi.org/10.3390/app16104673

Vancouver

Sigcha L, Pereira E, Borzì L, Gachet D, Cardoso P, Costa N. Enhancing Cross-Dataset Mental Workload Detection Using Electrodermal Activity and Domain Adaptation. Applied Sciences. 2026;16(10):4673. doi:10.3390/app16104673

BibTeX
@article{Sigcha2026,
  author = {Sigcha, Luis and Pereira, Eduarda and Borzì, Luigi and Gachet, Diego and Cardoso, Paulo and Costa, Nélson},
  title = {Enhancing Cross-Dataset Mental Workload Detection Using Electrodermal Activity and Domain Adaptation},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {10},
  pages = {4673},
  doi = {10.3390/app16104673}
}
Kostenlos starten →