A Convolutional Neural Network Integrating PPG Signal and Extracted Features for Dehydration Classification

• José Mateus Cordova Rodrigues UFAM
• Ayrton Finicelli Lemes UFAM
• Daniel Mitsuaki da Silva Utyiama UFAM
• Pedro Daniel da Silva Gohl UFAM
• Eduardo James Pereira Souto UFAM
• Rafael Giusti UFAM

DOI: https://doi.org/10.5753/eniac.2025.14491

Abstract

Dehydration is a serious health issue that can lead to serious consequences, making its accurate detection crucial to maintaining proper bodily function. In this work, we propose a hybrid machine learning model that can classify individuals into hydrated or dehydrated states. Our approach combines a shallow convolutional neural network that extracts unsupervised local features with statistical characteristics of time series data obtained from sensors such as Photoplethysmography (PPG) and Electrodermal Activity (EDA). The results show that the proposed classification model achieves an accuracy of 73%, which is superior to most existing works in the literature that use data extracted from PPG and/or EDA signals for the classification of hydration.

References

Akar, S. A., Kara, S., Latifoğlu, F., and Bilgic, V. (2013). Spectral analysis of photo-plethysmographic signals: The importance of preprocessing. Biomedical Signal Processing and Control, 8(1):16–22.

Alaslani, R., Perzhilla, L., Rahman, M. M. U., Laleg-Kirati, T.-M., and Al-Naffouri, T. Y. (2024). You can monitor your hydration level using your smartphone camera. arXiv preprint arXiv:2402.07467.

Armstrong, L. E. (2007). Assessing hydration status: the elusive gold standard. Journal of the American College of Nutrition, 26(sup5):575S–584S.

Blagus, R. and Lusa, L. (2013). Smote for high-dimensional class-imbalanced data. BMC bioinformatics, 14:1–16.

Cergolj, V., Stankoski, S., Pirc, M., and Luštrek, M. (2025). Drinking event detection on a sensing wristband using machine learning. Journal of Ambient Intelligence and Smart Environments, 17(2):164–181.

El-Sharkawy, A. M., Sahota, O., and Lobo, D. N. (2015). Acute and chronic effects of hydration status on health. Nutrition reviews, 73(suppl 2):97–109.

Gomes, D. and Sousa, I. (2019). Real-time drink trigger detection in free-living conditions using inertial sensors. Sensors, 19(9):2145.

Islam, T., Rigan, M. M. H., Bhuiyan, M. O. H., Hashem, T., and Rahman, M. M. (2025). H2opulse: Smartphone-assisted vein evaluation for early recognition of dehydration. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 9(2):1–24.

Kulkarni, N., Compton, C., Luna, J., and Alam, M. A. U. (2021). A non-invasive context-aware dehydration alert system. In Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications, pages 157–159.

Lee, J. W. and Kim, Y. (2024). Association of plain water intake with self-reported depression and suicidality among korean adolescents. Epidemiology and health, 46:e2024019.

Li, S., Xiao, X., and Zhang, X. (2024). Association between plain water intake and risk of hypertension: longitudinal analyses from the china health and nutrition survey. Frontiers in Public Health, 11:1280653.

Liaqat, S., Dashtipour, K., Arshad, K., and Ramzan, N. (2020). Non invasive skin hydration level detection using machine learning. Electronics, 9(7):1086.

Liaqat, S., Dashtipour, K., Rizwan, A., Usman, M., Shah, S. A., Arshad, K., Assaleh, K., and Ramzan, N. (2022). Personalized wearable electrodermal sensing-based human skin hydration level detection for sports, health and wellbeing. Scientific Reports, 12(1):3715.

Ortega Anderez, D., Lotfi, A., and Pourabdollah, A. (2021). A deep learning based wearable system for food and drink intake recognition. Journal of Ambient Intelligence and Humanized Computing, 12:9435–9447.

Plecher, D. A., Eichhorn, C., Lurz, M., Leipold, N., Böhm, M., Krcmar, H., Ott, A., Volkert, D., and Klinker, G. (2019). Interactive drinking gadget for the elderly and alzheimer patients. In Human Aspects of IT for the Aged Population. Social Media, Games and Assistive Environments: 5th International Conference, ITAP 2019, Held as Part of the 21st HCI International Conference, HCII 2019, Orlando, FL, USA, July 26-31, 2019, Proceedings, Part II 21, pages 444–463. Springer.

Popkin, B. M., D’Anci, K. E., and Rosenberg, I. H. (2010). Water, hydration, and health. Nutrition reviews, 68(8):439–458.

Posada-Quintero, H. F., Reljin, N., Moutran, A., Georgopalis, D., Lee, E. C.-H., Giersch, G. E., Casa, D. J., and Chon, K. H. (2019). Mild dehydration identification using machine learning to assess autonomic responses to cognitive stress. Nutrients, 12(1):42.

Reljin, N., Malyuta, Y., Zimmer, G., Mendelson, Y., Blehar, D. J., Darling, C. E., and Chon, K. H. (2018). Automatic detection of dehydration using support vector machines. In 2018 14th Symposium on Neural Networks and Applications (NEUREL), pages 1–6. IEEE.

Rizwan, A., Ali, N. A., Zoha, A., Ozturk, M., Alomainy, A., Imran, M. A., and Abbasi, Q. H. (2020). Non-invasive hydration level estimation in human body using galvanic skin response. IEEE Sensors Journal, 20(9):4891–4900.

Sabry, F., Eltaras, T., Labda, W., Hamza, F., Alzoubi, K., and Malluhi, Q. (2022). Towards on-device dehydration monitoring using machine learning from wearable device’s data. Sensors, 22(5):1887.

Siyoucef, S., Adnane, M., Rahman, M. M. U., Laleg-Kirati, T.-M., and Al-Naffouri, T. Y. (2025). Non-invasive monitoring of dehydration of fasting and sportspeople subjects via skin capacitance. IEEE Sensors journal.

Theodoridis, X., Poulia, K. A., and Chourdakis, M. (2025). What’s new about hydration in dementia? Current Opinion in Clinical Nutrition & Metabolic Care, 28(1):20–24.

Van Gent, P., Farah, H., Van Nes, N., and Van Arem, B. (2019). Heartpy: A novel heart rate algorithm for the analysis of noisy signals. Transportation research part F: traffic psychology and behaviour, 66:368–378.

van Iterson, H. C., Liang, R.-H., and Markopoulos, P. (2025). Redesigning fluid tracking probes for elderly lifestyle retrofit. In Proceedings of the Nineteenth International Conference on Tangible, Embedded, and Embodied Interaction, pages 1–6.