CLASSIFICATION OF HUMAN PHYSIOLOGICAL STATES USING HEART RATE, BLOOD PRESSURE, AND TEMPERATURE-BASED FEATURES

Authors

DOI:

https://doi.org/10.67772/8fsxv629

Keywords:

Physiological states, Heart rate, Blood pressure, Body temperature, Multinomial logistic regression

Abstract

Physiological signals such as heart rate, blood pressure, and body temperature provide important information about changes in human functional states. Their combined assessment may improve differentiation among activity, recovery, resting, sleep, and breathing conditions. The study aims to characterize cardiovascular and thermal features across different human physiological states, examine their associations, and assess their contribution to physiological-state classification. A secondary data-based analytical study was conducted using 1,806 observations representing seven physiological states: Cardio, Cardio Recovery, Resistance, Resistance Recovery, Sedentary, Sleep, and Deep Breathing. Frequency and percentage were used for categorical variables, while continuous variables were summarized as mean ± standard deviation. Chi-square tests assessed associations between physiological states and pre-to-post changes. Pearson correlation evaluated relationships among selected physiological measures, and multinomial logistic regression examined independent associations with state membership. Distinct cardiovascular and thermal response patterns were observed across physiological states. Activity-related conditions showed greater physiological activation, whereas recovery, sleep, and deep-breathing states demonstrated different patterns of reduction or stabilization. Chi-square analysis showed significant associations between physiological state and changes in heart rate, blood pressure, skin temperature, and core temperature. Strong correlations were observed among several cardiovascular and thermal variables. Multinomial regression did not identify a stable single independent predictor. Combined heart rate, blood pressure, and temperature-based features effectively characterize differences among human physiological states and may support non-invasive physiological monitoring applications.

References

1.Koul, S., Janani, L., Mir, M. S., Bashir, S., & Ahmad, S. T. (2026). Multimodal Framework for Truck Driver Vigilance and Driving Behavior Classification Using Physiological, Psychological, and Telemetry Data in Naturalistic Driving Conditions. Journal of The Institution of Engineers (India): Series A, 107(2), 323-344.

2.Fonda, H., Irawan, Y., Melyanti, R., Wahyuni, R., & Muhaimin, A. (2024). A comprehensive stacking ensemble approach for stress level classification in higher education. Journal of Applied Data Sciences, 5(4), 1701-1714.

3.Schmidt, P., Reiss, A., Dürichen, R., & Van Laerhoven, K. (2019). Wearable-based affect recognition—A review. Sensors, 19(19), 4079.

4.Bhavani, T., VamseeKrishna, P., Chakraborty, C., & Dwivedi, P. (2022). Stress classification and vital signs forecasting for IoT-health monitoring. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 21(4), 652-659.

5.Gioia, F., Greco, A., Callara, A. L., & Scilingo, E. P. (2022). Towards a contactless stress classification using thermal imaging. Sensors, 22(3), 976.

6.Wang, Z., Yu, Z., Zhao, B., Guo, B., Chen, C., & Yu, Z. (2020). Emotionsense: An adaptive emotion recognition system based on wearable smart devices. ACM Transactions on Computing for Healthcare, 1(4), 1-17.

7.Li, W., Chen, J., & Lan, F. (2022). Human thermal sensation algorithm modelization via physiological thermoregulatory responses based on dynamic thermal environment tests on males. Computer Methods and Programs in Biomedicine, 227, 107198.

8.Romine, W. L., Schroeder, N. L., Graft, J., Yang, F., Sadeghi, R., Zabihimayvan, M., ... & Banerjee, T. (2020). Using machine learning to train a wearable device for measuring students’ cognitive load during problem-solving activities based on electrodermal activity, body temperature, and heart rate: development of a cognitive load tracker for both personal and classroom use. Sensors, 20(17), 4833.

9.Mahmud, F., Quamruzzaman, M., Sanka, A. I., Cheung, R. C., & Chowdhury, M. H. (2026). Interpretable machine learning-based real-time sepsis diagnosis. Scientific Reports, 16(1), 6702.

10.Jegan, R., & Nimi, W. S. (2024). On the development of low power wearable devices for assessment of physiological vital parameters: a systematic review. Journal of Public Health, 32(7), 1093-1108.

11.Sahoh, B., Wongsontham, F., Tipsavak, A., Chaithong, P., Kliangkhlao, M., Efendi, M. A., ... & Punsawad, Y. (2026). Deep learning-based comparative evaluation of EEG, HRV, and EDA biomarkers for personal thermal comfort prediction. Biomedical Signal Processing and Control, 113, 108972.

12.Chaudhuri, T., Soh, Y. C., Li, H., & Xie, L. (2020). Machine learning driven personal comfort prediction by wearable sensing of pulse rate and skin temperature. Building and Environment, 170, 106615.

13.Chen, C. H., Lai, F., Chen, Y. L., & Guo, Y. L. (2025). Effects of Heat Adaptation Behaviors on Resting Heart Rate Response to Summer Temperatures in Older Adults: Wearable Device Panel Study. JMIR mHealth and uHealth, 13, e67721.

14.Rodrigues, M. C. J., Postolache, O., & Cercas, F. (2022). Unobtrusive cardio-respiratory assessment for different indoor environmental conditions. IEEE Sensors Journal, 22(23), 23243-23257.

15.Lu, E., Le, T. D., Jouvet, P., & Noumeir, R. (2025). Heart rate and body temperature relationship in children admitted to PICU: A machine learning approach. IEEE Transactions on Biomedical Engineering, 72(8), 2352-2365.

16.Ho, T. F., Tsai, H. H., Chuang, C. C., Lee, D., Huang, X. W., Chen, H., ... & Li, Y. H. (2024). Thermal comfort model established by using machine learning strategies based on physiological parameters in hot and cold environments. Indoor Air, 2024(1), 9427822.

17.Gouverneur, P., Li, F., Adamczyk, W. M., Szikszay, T. M., Luedtke, K., & Grzegorzek, M. (2021). Comparison of feature extraction methods for physiological signals for heat-based pain recognition. Sensors, 21(14), 4838.

18.Li, K., Liu, F., Luo, Y., & Khoso, M. A. (2025). Non-Invasive multivariate prediction of human thermal comfort based on facial temperatures and thermal adaptive action recognition. Energies, 18(9), 2332.

19.Arsalan, A., Majid, M., Nizami, I. F., Manzoor, W., Anwar, S. M., & Ryu, J. (2022). Human stress assessment: A comprehensive review of methods using wearable sensors and non-wearable techniques. arXiv preprint arXiv:2202.03033.

20.Cardone, D., & Merla, A. (2017). New frontiers for applications of thermal infrared imaging devices: Computational psychophysiology in the neurosciences. Sensors, 17(5), 1042.

21.Olyanasab, A., & Annabestani, M. (2024). Leveraging machine learning for personalized wearable biomedical devices: a review. Journal of personalized medicine, 14(2), 203.

22.Tai, Y., Obayashi, K., Okumura, K., Yamagami, Y., & Saeki, K. (2024). Blood pressure, pulse rate, and skin temperature during hot-water bathing in real-world settings among community-dwelling older adults: the HEIJO-KYO Study. Environmental Health and Preventive Medicine, 29, 12-12.

23.Šalkevicius, J., Damaševičius, R., Maskeliunas, R., & Laukienė, I. (2019). Anxiety level recognition for virtual reality therapy system using physiological signals. Electronics, 8(9), 1039.

Lee, J. T., Lee, P. F., & Pua, C. H. (2025). Physiological signal synthesis and classification: Assessing entropy change and other physiological signals [Data set]. Mendeley Data, Version 1. https://doi.org/10.17632/r43w3xkzyh.1

Downloads

Published

2026-10-27