EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Explainable Framework for Mental Health Monitoring Using Lightweight and Privacy-Preserving Federated Facial Emotion Recognition

Dina Shehada iD, Hissam Tawfik iD, Ahmed Bouridane iD, Abir Hussain iD

Sensors · 02.12.2025 · 25 (23) · 7320

DOI: 10.3390/s25237320 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.12.2025. Verfasst von Dina Shehada und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, University of Sharjah, Sharjah P.O. Box 27272, United Arab Emirates. Hauptthemen laut MEDLINE: Emotions, Mental Health, Facial Recognition. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The continuous analysis of emotional cues through facial emotion recognition (FER) systems can support mental health evaluation and psychological well-being monitoring systems. Most FER systems face privacy and trust concerns due to their centralized data approaches and lack of transparency, making potential deployment difficult. To address these concerns, a federated, explainability-driven FER framework designed to provide trustworthy and privacy-preserving emotion recognition with potential applications in mental health monitoring is proposed in this paper. The proposed lightweight Convolutional Neural Network (CNN) enables real-time inference while preserving high accuracy. Comprehensive evaluations on RAF-DB, ExpW, and FER2013 datasets, show that the proposed model demonstrates improved cross-dataset generalization compared to related works, achieving average accuracies of 75.5% and 74.3% in centralized and federated settings, respectively. Quantitative perturbation-based metrics, including Insertion and Deletion Area Under Curve (IAUC and DAUC), Average Drop (AD), Increase in Confidence (IC), Average Drop in Accuracy (ADA), and Active Pixel Ratio, were employed to objectively evaluate the quality and reliability of the model Grad-CAM++ explanations. The results confirm that model explainability enhances transparency and is directly associated with improved model performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EmotionsMental HealthFacial RecognitionHumansNeural Networks, ComputerPrivacyFacial ExpressionAlgorithms

Stichwörter der Autor:innen

assistive technologyexplainable AI (XAI)facial emotion recognition (FER)federated learningmodel interpretabilitytrustworthy AI

Autor:innen und Institutionen

  • Department of Electrical Engineering, University of Sharjah, Sharjah P.O. Box 27272, United Arab Emirates.
  • Department of Engineering and Information Technology, University of Dubai, Dubai P.O. Box 14143, United Arab Emirates.
  • School of Built Environment, Engineering and Computing, Leeds Beckett University, Leeds LS1 3HE, UK.
  • College of Computing and Informatics, University of Sharjah, Sharjah P.O. Box 27272, United Arab Emirates.

ORCID-Profile: Dina Shehada, Hissam Tawfik, Ahmed Bouridane, Abir Hussain

Zitieren

APA

Shehada, D., Tawfik, H., Bouridane, A., & Hussain, A. (2025). An Explainable Framework for Mental Health Monitoring Using Lightweight and Privacy-Preserving Federated Facial Emotion Recognition. Sensors, 25(23), 7320. https://doi.org/10.3390/s25237320

Vancouver

Shehada D, Tawfik H, Bouridane A, Hussain A. An Explainable Framework for Mental Health Monitoring Using Lightweight and Privacy-Preserving Federated Facial Emotion Recognition. Sensors. 2025;25(23):7320. doi:10.3390/s25237320

BibTeX
@article{Shehada2025,
  author = {Shehada, Dina and Tawfik, Hissam and Bouridane, Ahmed and Hussain, Abir},
  title = {An Explainable Framework for Mental Health Monitoring Using Lightweight and Privacy-Preserving Federated Facial Emotion Recognition},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {23},
  pages = {7320},
  doi = {10.3390/s25237320}
}
Kostenlos starten →