EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cost-Effective Mood Detection Through IoT Wearable Sensors and Machine Learning Classification

Soran Bakhtyar Noori, Dler Salih Hassan

Zanco Journal of Pure and Applied Sciences · 30.06.2026 · 38 (3) · 214-226

DOI: 10.21271/zjpas.38.3.16 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Zanco Journal of Pure and Applied Sciences, online erschienen am 30.06.2026. Verfasst von Soran Bakhtyar Noori und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A cost-effective wearable Internet of Things (IoT) system is presented for real-time mood and stress detection using MAX30100 photoplethysmography, galvanic skin response (GSR), and MLX90614 wrist temperature sensors integrated with a Raspberry Pi edge device. Physiological signals are acquired, preprocessed on-device, segmented into 60 s windows with 50% overlap, and transformed into heart-rate variability, GSR, and temperature features. Six machine-learning classifiers are trained and evaluated with support from the WESAD dataset and a custom dataset collected from 25 participants, using a single stratified 70/30 train–test split and leave-one-subject-out cross-validation. Results indicate that low-cost hardware and lightweight models can achieve promising performance for real-time mood and stress monitoring, suggesting feasibility for mobile and ambulatory healthcare applications. Future work will extend deployment to a mobile companion app with real-time alerts, increase cohort size for stronger subject-independent validation, and explore compact deep models while preserving on-device privacy.

Zitieren

APA

Noori, S. B., & Hassan, D. S. (2026). Cost-Effective Mood Detection Through IoT Wearable Sensors and Machine Learning Classification. Zanco Journal of Pure and Applied Sciences, 38(3), 214-226. https://doi.org/10.21271/zjpas.38.3.16

Vancouver

Noori SB, Hassan DS. Cost-Effective Mood Detection Through IoT Wearable Sensors and Machine Learning Classification. Zanco Journal of Pure and Applied Sciences. 2026;38(3):214-226. doi:10.21271/zjpas.38.3.16

BibTeX
@article{Noori2026,
  author = {Noori, Soran Bakhtyar and Hassan, Dler Salih},
  title = {Cost-Effective Mood Detection Through IoT Wearable Sensors and Machine Learning Classification},
  journal = {Zanco Journal of Pure and Applied Sciences},
  year = {2026},
  volume = {38},
  number = {3},
  pages = {214--226},
  doi = {10.21271/zjpas.38.3.16}
}
Kostenlos starten →