EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Pain Assessment from Electrodermal Activity Using Deep Learning

Calvin Joseph iD, Maryam Ghahramani iD, Raul Fernandez Rojas iD

Sensors · 2026

DOI: 10.3390/s26103020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Calvin Joseph und 2 weiteren Autor:innen. Beteiligte Einrichtung: Biosensing and Intelligent Systems (BioSIS) Lab, Centre for Intelligent Computing and Systems (CICS), University of Canberra, Canberra, ACT 2617, Aus…. Hauptthemen laut MEDLINE: Deep Learning, Galvanic Skin Response, Pain Measurement, Pain. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective pain assessment remains a significant challenge in clinical and research settings due to the subjective nature of self-reported measures. Physiological signals, particularly electrodermal activity (EDA), have emerged as promising indicators of autonomic responses associated with pain. Although recent advances in deep learning have improved the modelling of complex biosignals, many existing approaches remain computationally demanding, limiting their applicability for real-time monitoring in wearable and embedded systems. This paper proposes a fully convolutional network (FCN) for automated pain recognition using EDA signals. The proposed model is designed to efficiently capture temporal patterns in physiological data while maintaining low computational complexity. The approach is evaluated on the AI4Pain dataset for three-class pain classification (No Pain, Low Pain, High Pain). Experimental results show that the proposed FCN achieves an accuracy of 79.23% in offline evaluation. Furthermore, the model enables real-time inference with a latency of 0.47 ms, achieving 73.14% accuracy during real-time operation. These results demonstrate that convolutional architectures can provide an effective balance between predictive performance and computational efficiency, supporting the development of real-time physiological pain monitoring systems using wearable sensing technologies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGalvanic Skin ResponsePain MeasurementPainHumansWearable Electronic DevicesConvolutional Neural NetworksSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

continuous monitoringdeep learningelectrodermal activitypain assessmentreal time monitoring

Autor:innen und Institutionen

  • Biosensing and Intelligent Systems (BioSIS) Lab, Centre for Intelligent Computing and Systems (CICS), University of Canberra, Canberra, ACT 2617, Australia.

ORCID-Profile: Calvin Joseph, Maryam Ghahramani, Raul Fernandez Rojas

Zitieren

APA

Joseph, C., Ghahramani, M., & Rojas, R. F. (2026). Real-Time Pain Assessment from Electrodermal Activity Using Deep Learning. Sensors. https://doi.org/10.3390/s26103020

Vancouver

Joseph C, Ghahramani M, Rojas RF. Real-Time Pain Assessment from Electrodermal Activity Using Deep Learning. Sensors. 2026. doi:10.3390/s26103020

BibTeX
@article{Joseph2026,
  author = {Joseph, Calvin and Ghahramani, Maryam and Rojas, Raul Fernandez},
  title = {Real-Time Pain Assessment from Electrodermal Activity Using Deep Learning},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26103020}
}
Kostenlos starten →