EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Continuous Emotion Recognition Using EDA-Graphs: A Graph Signal Processing Approach for Affective Dimension Estimation

Luis R Mercado-Diaz iD, Youngsun Kong iD, Josef Kundrát iD, Hugo F Posada-Quintero iD

Applied Sciences · 27.03.2026 · 16 (7) · 3240

DOI: 10.3390/app16073240 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 27.03.2026. Verfasst von Luis R Mercado-Diaz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, University of Connecticut, Storrs, CT 06269, USA. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 84 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIDDK NIH HHS, National Institute of Diabetes and Digestive and Kidney Diseases https://ror.org/00adh9b73, Fulbright–Masaryk Scholarship Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Emotion recognition from physiological signals has immense applications in healthcare and human–computer interaction. We developed an electrodermal activity (EDA)-graph signal processing pipeline that produces highly sensitive features for detecting the affective dimensions (arousal and valence) of emotions. Using the Continuously Annotated Signals of Emotion dataset, we compared our graph-based EDA features (EDA-graph) with traditional time- and frequency-domain EDA features and features derived from other signals (heart rate variability, pulse transit time, electromyography, skin temperature, and respiration) for detecting affective dimensions using machine learning regression models. The EDA-graph features showed superior performance in continuous affective dimension recognition compared to the most accurate state-of-the-art models, achieving RMSE values of 0.801 for arousal and 0.714 for valence. Furthermore, we used a variety of traditional and recently published datasets collected in laboratory and ambulatory settings to perform a comprehensive evaluation of the robust generalization capabilities of our approach across different emotional contexts. The models demonstrated exceptional performance in classifying emotional states across the datasets, achieving 98.2% accuracy in detecting positive, negative, and mixed emotions; 92.75% in discriminating between emotions (relaxed, amused, bored, scared, and neutral); and 86.54% in detecting stress vs. no stress. These results highlight the potential of a graph-based analysis of EDA in emotion recognition systems in different contexts, especially for real-world applications.

Schlagwörter

Stichwörter der Autor:innen

affective dimensionsarousalelectrodermal activityemotion recognitionemotional statesgraph signal processingmachine learningvalence

Autor:innen und Institutionen

  • Department of Biomedical Engineering, University of Connecticut, Storrs, CT 06269, USA.
  • Department of Psychology, Faculty of Arts, University of Ostrava, Dvořákova 138/7, 701 03 Ostrava, Czech Republic.

ORCID-Profile: Luis R Mercado-Diaz, Youngsun Kong, Josef Kundrát, Hugo F Posada-Quintero

Förderung

  • NIDDK NIH HHS
  • National Institute of Diabetes and Digestive and Kidney Diseases https://ror.org/00adh9b73
  • Fulbright–Masaryk Scholarship Program

Zitieren

APA

Mercado-Diaz, L. R., Kong, Y., Kundrát, J., & Posada-Quintero, H. F. (2026). Continuous Emotion Recognition Using EDA-Graphs: A Graph Signal Processing Approach for Affective Dimension Estimation. Applied Sciences, 16(7), 3240. https://doi.org/10.3390/app16073240

Vancouver

Mercado-Diaz LR, Kong Y, Kundrát J, Posada-Quintero HF. Continuous Emotion Recognition Using EDA-Graphs: A Graph Signal Processing Approach for Affective Dimension Estimation. Applied Sciences. 2026;16(7):3240. doi:10.3390/app16073240

BibTeX
@article{MercadoDiaz2026,
  author = {Mercado-Diaz, Luis R and Kong, Youngsun and Kundrát, Josef and Posada-Quintero, Hugo F},
  title = {Continuous Emotion Recognition Using EDA-Graphs: A Graph Signal Processing Approach for Affective Dimension Estimation},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {7},
  pages = {3240},
  doi = {10.3390/app16073240}
}
Kostenlos starten →