Integration of Subjective and Emotional Physiological Data for Classifying Sleep Quality with Machine Learning

• Nicolly Alves da Silva UFAM
• Hygo Sousa de Oliveira UFAM
• Eduardo James Pereira Souto UFAM
• Rafael Giusti UFAM

DOI: https://doi.org/10.5753/eniac.2025.14363

Abstract

Sleep quality is a critical factor for physical and mental health, directly associated with conditions such as anxiety, cardiovascular diseases, and metabolic disorders. This study proposes a machine learning pipeline to classify sleep quality as “good” or “poor” by integrating physiological (actigraphy), subjective (PSQI), and emotional (STAI-Y2) data. Experiments were conducted using the MMASH dataset with Leave-One-Subject-Out (LOSO) validation, strengthening the generalizability of the results. The proposed methodology achieved up to 0.98 ± 0.01 accuracy with a neural network, outperforming related studies that employed less rigorous validation protocols. These findings demonstrate the feasibility of combining multiple data dimensions for non-invasive monitoring, with potential applications in wearable devices and personalized sleep health interventions.

References

Acharya, J. (2020). Design and development of a method for detecting sleep roll-over counts using accelerometer adxl335. International Journal of Electrical & Computer Engineering (2088-8708), 10(1).

Angelova, M., Karmakar, C., Zhu, Y., Drummond, S. P., and Ellis, J. (2020). Automated method for detecting acute insomnia using multi-night actigraphy data. IEEE Access, 8:74413–74422.

Bitkina, O. V., Park, J., and Kim, J. (2022). Modeling sleep quality depending on objective actigraphic indicators based on machine learning methods. International Journal of Environmental Research and Public Health, 19(16):9890.

Buysse, D. J., Reynolds III, C. F., Monk, T. H., Berman, S. R., and Kupfer, D. J. (1989). The pittsburgh sleep quality index: a new instrument for psychiatric practice and research. Psychiatry research, 28(2):193–213.

Cole, R. J., Kripke, D. F., Gruen, W., Mullaney, D. J., and Gillin, J. C. (1992). Automatic sleep/wake identification from wrist activity. Sleep, 15(5):461–469.

Conte, F., De Rosa, O., Rescott, M. L., Arabia, T. P., D’Onofrio, P., Lustro, A., Malloggi, S., Molinaro, D., Spagnoli, P., Giganti, F., et al. (2022). High sleep fragmentation parallels poor subjective sleep quality during the third wave of the covid-19 pandemic: An actigraphic study. Journal of sleep research, 31(3):e13519.

Fekedulegn, D., Andrew, M. E., Shi, M., Violanti, J. M., Knox, S., and Innes, K. E. (2020). Actigraphy-based assessment of sleep parameters. Annals of Work Exposures and Health, 64(4):350–367.

Gardani, M., Bradford, D. R., Russell, K., Allan, S., Beattie, L., Ellis, J. G., and Akram, U. (2022). A systematic review and meta-analysis of poor sleep, insomnia symptoms and stress in undergraduate students. Sleep medicine reviews, 61:101565.

Geng, D., Qin, Z., Wang, J., Gao, Z., and Zhao, N. (2022). Personalized recognition of wake/sleep state based on the combined shapelets and k-means algorithm. Biomedical Signal Processing and Control, 71:103132.

Hussain, Z., Sheng, Q. Z., Zhang, W. E., Ortiz, J., and Pouriyeh, S. (2022). Non-invasive techniques for monitoring different aspects of sleep: A comprehensive review. ACM Transactions on Computing for Healthcare (HEALTH), 3(2):1–26.

Pan, Q., Brulin, D., and Campo, E. (2020). Current status and future challenges of sleep monitoring systems: Systematic review. JMIR Biomedical Engineering, 5(1):e20921.

Rossi, A., Da Pozzo, E., Menicagli, D., Tremolanti, C., Priami, C., Sirbu, A., Clifton, D., Martini, C., and Morelli, D. (2020). Multilevel monitoring of activity and sleep in healthy people (version 1.0. 0). physionet, 2020.

Sano, A., Rahman, T., Zhang, M., Ganesan, D., and Choudhury, T. (2020). Mobile sensing of alertness, sleep and circadian rhythm: Hardware & software platforms. GetMobile: Mobile Computing and Communications, 23(3):16–22.

Sathyanarayana, A., Joty, S., Fernandez-Luque, L., Ofli, F., Srivastava, J., Elmagarmid, A., Arora, T., and Taheri, S. (2016). Sleep quality prediction from wearable data using deep learning. JMIR mHealth and uHealth, 4(4):e6562.

Site, A., Lohan, E. S., Jolanki, O., Valkama, O., Hernandez, R. R., Latikka, R., Alekseeva, D., Vasudevan, S., Afolaranmi, S., Ometov, A., et al. (2022). Managing perceived loneliness and social-isolation levels for older adults: a survey with focus on wearables-based solutions. Sensors, 22(3):1108.