EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deployment of TinyML-Based Stress Classification Using Computational Constrained Health Wearable

Asma Abu-Samah, Dalilah Ghaffa, Nor Fadzilah Abdullah, Noorfazila Kamal, Rosdiadee Nordin, Jennifer C. Dela Cruz, Glenn V. Magwili, Reginald Juan Mercado

Electronics · 10.02.2025 · 14 (4) · 687

DOI: 10.3390/electronics14040687 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 10.02.2025. Verfasst von Asma Abu-Samah und 7 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NICT Japan, Universiti Kebangsaan Malaysia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Stress has become a common mental health issue in modern society, causing individuals to experience acute behavioral changes. Exposure to prolonged stress without proper prevention and treatment may cause severe damage to one’s physiological and psychological health. Researchers around the world have been working to find and create solutions for early stress detection using machine learning (ML). This paper investigates the possibility of utilizing Tiny Machine Learning (TinyML) in developing a wearable device, comparable to a smartwatch, that is equipped with both physiological and psychological data detection system to enable edge computing and give immediate feedback for stress prediction. The main challenge of this study was to fit a trained ML model into the microcontroller’s limited memory without compromising the model’s accuracy. A TinyML-based framework using a Raspberry Pi Pico RP2040 on a customized board equipped with several health sensors was proposed to predict stress levels by utilizing accelerations, body temperature, heart rate, and electrodermal activity from a public health dataset. Moreover, a few selected machine learning models underwent hyperparameter tuning before a porting library was used to translate them from Python to C/C++ for deployment. This approach led to an optimized XGBoost model with 86.0% accuracy and only 1.12 MB in size, hence perfectly fitting into the 2 MB constraint of RP2040. The prediction of stress on the edge device was then tested and validated using a separate sub-dataset. This trained model on TinyML can also be used to obtain an immediate reading from the calibrated health sensors for real-time stress predictions.

Förderung

  • NICT Japan
  • Universiti Kebangsaan Malaysia

Zitieren

APA

Abu-Samah, A., Ghaffa, D., Abdullah, N. F., Kamal, N., Nordin, R., Cruz, J. C. D., Magwili, G. V., & Mercado, R. J. (2025). Deployment of TinyML-Based Stress Classification Using Computational Constrained Health Wearable. Electronics, 14(4), 687. https://doi.org/10.3390/electronics14040687

Vancouver

Abu-Samah A, Ghaffa D, Abdullah NF, Kamal N, Nordin R, Cruz JCD, et al. Deployment of TinyML-Based Stress Classification Using Computational Constrained Health Wearable. Electronics. 2025;14(4):687. doi:10.3390/electronics14040687

BibTeX
@article{AbuSamah2025,
  author = {Abu-Samah, Asma and Ghaffa, Dalilah and Abdullah, Nor Fadzilah and Kamal, Noorfazila and Nordin, Rosdiadee and Cruz, Jennifer C. Dela and Magwili, Glenn V. and Mercado, Reginald Juan},
  title = {Deployment of TinyML-Based Stress Classification Using Computational Constrained Health Wearable},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {4},
  pages = {687},
  doi = {10.3390/electronics14040687}
}
Kostenlos starten →