Real-time stress detection using IoT devices and deep learning

• Gabriel Fernandes UFJF
• Luiz Nazareth UFJF
• Rubia Viol UFJF
• Victor Ströele UFJF

DOI: https://doi.org/10.5753/sbcup.2025.9297

Abstract

Chronic diseases, such as cardiovascular disease, diabetes, and cancer, have daily stress as a relevant factor in their progression. This study proposes a deep learning architecture to detect real-time stress episodes. Data from IoT devices on the individual’s heart rate and location was used to do this. A mobile system processes this data, identifies stress patterns, and sends real-time notifications to the user. The results show that with the approach developed, it is possible to detect episodes of stress, providing real-time alerts to the user.

References

Bauer, M. E. (2002). Estresse. Ciência hoje, 30(179):20–25.

Can, Y. S., Chalabianloo, N., Ekiz, D., Fernandez-Alvarez, J., Repetto, C., Riva, G., Iles-Smith, H., and Ersoy, C. (2020). Real-life stress level monitoring using smart bands in the light of contextual information. IEEE Sensors Journal, 20(15):8721–8730.

Chollet, F. (2015). Keras. Accessed: 2024-05-15.

Dieleman, J. L., Cao, J., Chapin, A., Chen, C., Li, Z., Liu, A., Horst, C., Kaldjian, A., Matyasz, T., Scott, K. W., et al. (2020). Us health care spending by payer and health condition, 1996-2016. Jama, 323(9):863–884.

Foundation, A. S. (2024). Apache airflow.

Gedam, S. and Paul, S. (2021). A review on mental stress detection using wearable sensors and machine learning techniques. IEEE Access, 9:84045–84066.

Nurmi, J. and Lohan, E. S. (2021). Systematic review on machine-learning algorithms used in wearable-based ehealth data analysis. IEEE Access, 9:112221–112235.

Risch, M., Grossmann, K., Aeschbacher, S., Weideli, O. C., Kovac, M., Pereira, F., Wohlwend, N., Risch, C., Hillmann, D., Lung, T., et al. (2022). Investigation of the use of a sensor bracelet for the presymptomatic detection of changes in physiological parameters related to covid-19: an interim analysis of a prospective cohort study (covi-gapp). BMJ open, 12(6):e058274.

Sergio, W. L., di Iorio Silva, G., Ströele, V., and Dantas, M. A. R. (2023). An Architecture Proposal to Support E-Healthcare Notifications, page 157–170. Springer International Publishing.

Zhao, L., Niu, X., Wang, L., Niu, J., Zhu, X., and Dai, Z. (2023). Stress detection via multimodal multitemporal-scale fusion: A hybrid of deep learning and handcrafted feature approach. IEEE Sensors Journal, 23(22):27817–27827.