Integrating Heart Rate Data into Machine Learning Models of Indoor Thermal Comfort Prediction

Ismail Ishaq Ibrahim; Shazmin Aniza Abdul Shukor; Muhajir Ab Rahim

doi:10.58915/aset.v5i2.3100

Authors

Ismail Ishaq Ibrahim Universiti Malaysia Perlis
Shazmin Aniza Abdul Shukor Universiti Malaysia Perlis
Muhajir Ab Rahim Universiti Malaysia Perlis

DOI:

https://doi.org/10.58915/aset.v5i2.3100

Keywords:

Heart Rate, Machine Learning, Physiological Sensing, Predicted Mean Vote (PMV), Thermal Comfort

Abstract

Maintaining occupant comfort necessitates accurate, real-time thermal comfort models. The Predicted Mean Vote (PMV) is a cornerstone index, but its calculation requires parameters that are often impractical to measure directly. Integrating heart rate will facilitate personalized comfort models. Further, it could anticipate comfort needs and make proactive adjustments when needed. Machine learning can enhance predictive accuracy of the models, and it enables continuous learning adaptation to changing conditions. This study leverages the computational environment of MATLAB to develop and compare two machine learning-based models, Support Vector Machine (SVM) and Random Forest (RF), for predicting PMV using heart rate (HR), air temperature (Ta), and relative humidity (RH). Both models were trained and evaluated based on Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R²). This research concludes that RF provides a robust and accurate data-driven framework for real-time PMV prediction, paving the way for enhanced, physiology-responsive systems that can be used to achieve significant gains in energy resiliency and systematic sustainability from excessive carbon expenditure while simultaneously enhancing human bioclimatic comfort. This research also exemplifies the Smart Structure (SDG 11) mandate. It upgrades standard building hardware with IoT-driven intelligence, moving towards a resilient, sustainable and safe ecosystem.

References

[1] Shukor, S. A. A., Kohlhof, K., Jamal, Z. A. Z. Development of a PMV-based thermal comfort modelling. Proceedings of the IASTED International Conference on Modelling and Simulation, issue June 2019 (2007) pp.670-675.

[2] Bogatu, D. I., et al. Human physiology for personal thermal comfort-based HVAC control - A review. Elsevier Ltd., (2023). https://doi.org/10.1016/j.buildenv.2023.110418

[3] Avelino, A. D., da Silva, L. B. PMV as a thermal evaluation method for air-conditioned spaces in hot climates: A systematic review. Ciência e Natura, vol 42 (2020) pp.e29. https://doi.org/10.5902/2179460X41375

[4] Liu, S., Schiavon, S., Das, H. P., Jin, M., Spanos, C. J. Personal thermal comfort models with wearable sensors. Build. Environ., vol 162, issue July (2019). https://doi.org/10.1016/j.buildenv.2019.106281

[5] Jung, D., Cheon, S., Kim, D., Yoon, J., Member, B. K. Short time remote heart rate measurement based on mmWave FMCW radar frame structure. vol 14, issue 8 (2023). https://doi.org/10.1109/LAWP.2023.3241153

[6] Lala, B., Kala, S. M., Rastogi, A., Dahiya, K., Hagishima, A. Are you comfortable now: Deep learning the temporal variation in thermal comfort in winters. Conf. Proc. IEEE Int. Conf. Syst. Man Cybern., vol 2022-Octob (2022) pp.1848-1855. https://doi.org/10.1109/SMC53654.2022.9945533

[7] Chen, Y., Liang, E., Berardi, U., Yang, J., Jiang, X., Cui, G. A model-based predictive control method of the ground-source heat pump system for maintaining thermal comfort in low-energy buildings. 2022 IEEE 7th International Conference on Power and Renewable Energy, ICPRE 2022, issue 52108100 (2022) pp.1080-1085. https://doi.org/10.1109/ICPRE55555.2022.9960567

[8] Huang, K., Lu, S., Li, X., Feng, K., Chen, W., Xia, Y. Predicted mean vote of subway car environment based on machine learning. Big Data Mining and Analytics, vol 6, issue 1 (2023) pp.92-105. https://doi.org/10.26599/BDMA.2022.9020028

[9] Liu, W., Lian, Z., Liu, Y. Heart rate variability at different thermal comfort levels. Eur. J. Appl. Physiol., vol 103, issue 3 (2008) pp.361-366. https://doi.org/10.1007/s00421-008-0718-6

[10] Fayyaz, M., Farhan, A. A., Javed, A. R. Thermal comfort model for HVAC buildings using machine learning. Arab. J. Sci. Eng., vol 47, issue 2 (2022) pp.2045-2060. https://doi.org/10.1007/s13369-021-06156-8

[11] Pao, S. L., et al. A physiological-signal-based thermal sensation model for indoor environment thermal comfort evaluation. Int. J. Environ. Res. Public Health, vol 19, issue 12 (2022) pp.1-16. https://doi.org/10.3390/ijerph19127292

[12] Ihianle, I. K., MacHado, P., Owa, K., Adama, D. A. Towards achieving thermal comfort through physiologically controlled HVAC system. International Conference Automatics and Informatics, ICAI 2022 - Proceedings, (2022) pp.245-249. https://doi.org/10.1109/ICAI55857.2022.9960018

[13] Zhan, J., He, W. Evaluation and prediction of elderly thermal comfort at varying ambient temperatures based on electroencephalogram signals and machine learning. Proceedings - 2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2022, issue 52078281 (2022) pp.0-4. https://doi.org/10.1109/CISP-BMEI56279.2022.9980300

[14] Nkurikiyeyezu, K., Shoji, K., Yokokubo, A., Lopez, G. Thermal comfort and stress recognition in office environment. HEALTHINF 2019 - 12th International Conference on Health Informatics, Proceedings https://doi.org/10.5220/0007368802560263

[15] Part of 12th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2019, issue Biostec (2019) pp.256-263.

[16] Nkurikiyeyezu, K. N., Suzuki, Y., Lopez, G. F. Heart rate variability as a predictive biomarker of thermal comfort. J. Ambient Intell. Humaniz. Comput., vol 9, issue 5 (2018) pp.1465-1477. https://doi.org/10.1007/s12652-017-0567-4

[17] Bosch. Bosch BMP280 datasheet. (2021).

[18] Patil, A., Hulwan, S. Heart-rate variability estimation using photoplethysmography signal. vol 9, issue 2 (2020) pp.67-74.

[19] Sung, W. T., Shih, J. A. Indoor thermal comfort environment monitoring system based on architecture of IoT. Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018, (2019) pp.165-168. https://doi.org/10.1109/IS3C.2018.00049

[20] Hormazábal, N., Franco, P., Urtubia, D., Ahmed, M. A. Data-driven smart avatar for thermal comfort evaluation in Chile. Buildings, vol 13, issue 8 (2023) pp.1-24. https://doi.org/10.3390/buildings13081953

[21] Ma, Y., Chen, C., Zeng, S., Guan, X., Lu, C. Data-driven edge offloading for wireless control. (2023) pp.1-16.

[22] Morresi, N., et al. Sensing physiological and environmental quantities to measure human thermal comfort through machine learning techniques. IEEE Sens. J., vol 21, issue 10 (2021) pp.12322-12337. https://doi.org/10.1109/JSEN.2021.3064707

[23] Zhou, Z., Qiu, C., Zhang, Y. A comparative analysis of linear regression, neural networks and random forest regression for predicting air ozone employing soft sensor models. Sci. Rep., vol 13, issue 1 (2023). https://doi.org/10.1038/s41598-023-49899-0