Machine Learning-Based Predictive Models for Indoor Air Quality and Thermal Comfort: Bridging Sensor Data and Human Perception in Healthcare Facilities
, , , , , , , , , , ,
1Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, 40450 Shah Alam, Malaysia; Department of Architecture and Built Environment, The University of Nottingham, University Park, Nottingham, NG7 2RD, United Kingdom
2Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, 02600 Arau, Malaysia
3Solar Energy Research Institute. The National University of Malaysia, 43600 Bangi Selangor, Malaysia; Department of Architecture and Built Environment, The University of Nottingham, University Park, Nottingham, NG7 2RD, United Kingdom
4Department of Earth Sciences and Environment, Faculty of Science and Technology, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia
5Department of Architecture and Built Environment, The University of Nottingham, University Park, Nottingham, NG7 2RD, United Kingdom
6Faculty of Electrical Technology and Engineering, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal Melaka, Malaysia
7Solar Energy Research Institute. The National University of Malaysia, 43600 Bangi Selangor, Malaysia
8Engineering Services Division, Ministry of Health Malaysia, 62590, Putrajaya, Malaysia
Poor indoor air quality (IAQ) and inadequate thermal comfort continue to challenge healthcare facilities in Malaysia, especially in rural areas where poor ventilation and high humidity are prevalent. These environmental stressors negatively impact patient outcomes, staff well-being, and operational efficiency. Existing solutions often overlook the integration of subjective human perception with objective sensor data, resulting in limited adaptability and responsiveness. This study introduces a datadriven, human-centric framework that combines environmental sensor measurements with user-reported comfort feedback to develop predictive models for IAQ and thermal comfort. A comprehensive machine learning pipeline was implemented using four algorithms—Random Forest (RF), XGBoost, Artificial Neural Network (ANN), and Support Vector Machine (SVM)—to model both continuous IAQ indicators and categorical thermal preferences. Experimental results show that Random Forest achieved the best overall performance, with the lowest root mean squared error (RMSE = 14.35) in regression and the highest classification accuracy (87.5%) in predicting thermal preference. Statistical validation confirmed that Random Forest and XGBoost performed similarly in regression, while Random Forest and SVM showed no significant differences in classification accuracy. These findings validate Random Forest as a robust and consistent model across both tasks. This study contributes a validated, AI-enhanced framework for intelligent environmental monitoring in healthcare settings, emphasizing the integration of subjective and objective data streams. The approach supports personalized, data-driven interventions and offers practical insights for facility managers, clinicians, and policymakers aiming to optimize indoor conditions. Future work will focus on scaling the dataset across diverse facilities and climates, enabling real-time deployment, and incorporating explainable AI techniques to enhance model transparency and stakeholder trust.
J. Khodakarami and N. Nasrollahi, “Thermal comfort in hospitals – A literature review,” Renewable and Sustainable Energy Reviews, vol. 16, no. 6, pp. 4071–4077, Aug. 2012, doi: 10.1016/J.RSER.2012.03.054.
A. A. Aziz, D. Sumiyoshi, and Y. Akashi, “Low cost humidity controlled air-conditioning system for building energy savings in tropical climate,” Journal of Building Engineering, vol. 11, pp. 9–16, May 2017, doi: 10.1016/J.JOBE.2017.03.005.
Z. Wang et al., “Individual difference in thermal comfort: A literature review,” Build Environ, vol. 138, pp. 181–193, Jun. 2018, doi: 10.1016/J.BUILDENV.2018.04.040.
C. A. Balaras, E. Dascalaki, and A. Gaglia, “HVAC and indoor thermal conditions in hospital operating rooms,” Energy Build, vol. 39, no. 4, pp. 454–470, Apr. 2007, doi: 10.1016/J.ENBUILD.2006.09.004.
C. Fan, Y. Sun, Y. Zhao, M. Song, and J. Wang, “Deep learning-based feature engineering methods for improved building energy prediction,” Appl Energy, vol. 240, pp. 35–45, Apr. 2019, doi: 10.1016/J.APENERGY.2019.02.052.
H. Q. Flayyih, J. Waleed, and A. M. Ibrahim, “IoT- based AI Methods for Indoor Air Quality Monitoring Systems: A Systematic Review,” International Journal of Computing and Digital Systems, vol. 16, no. 1, pp. 813–826, Jul. 2024, doi: 10.12785/IJCDS/160159.
A. Singh, M. Islam, and N. Dinh, “Forecasting Indoor Air Quality Using Machine Learning Models,” Digest of Technical Papers - IEEE International Conference on Consumer Electronics, 2024, doi: 10.1109/ICCE59016.2024.10444387.
M. W. Ahmad, M. Mourshed, and Y. Rezgui, “Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption,” Energy Build, vol. 147, pp. 77–89, Jul. 2017, doi: 10.1016/J.ENBUILD.2017.04.038.
Y. H. Yau and B. T. Chew, “A review on predicted mean vote and adaptive thermal comfort models,” vol. 35, no. 1, pp. 23–35, Oct. 2012, doi: 10.1177/0143624412465200.
A. Baudet, E. Baurès, O. Blanchard, P. Le Cann, J. P. Gangneux, and A. Florentin, “Indoor Carbon Dioxide, Fine Particulate Matter and Total Volatile Organic Compounds in Private Healthcare and Elderly Care Facilities,” Toxics, vol. 10, no. 3, Mar. 2022, doi: 10.3390/TOXICS10030136.
Y. Yusup, M. I. Ahmad, and N. Ismail, “Indoor Air Quality of Typical Malaysian Open-air Restaurants,” Environment and Pollution, vol. 3, no. 4, Aug. 2014, doi: 10.5539/EP.V3N4P10.
W. A. Rahman, H. Rosli, S. N. Baharuddin, and B. Salleh, “Incidence and remediation of fungi in a sick building in Malaysia: a case study,” Aerobiologia (Bologna), vol. 28, no. 2, pp. 275– 283, Jun. 2012, doi: 10.1007/S10453-011-9226-Y.
I. A. Rahman, J. C. P. Putra, and S. Nagapan, “Correlation of Indoor Air Quality with Working Performance in Office Building,” Mod Appl Sci, vol. 8, no. 6, pp. 153–160, 2014, doi: 10.5539/MAS.V8N6P153.
M. El-Sharkawy and M. Noweir, “Indoor air quality levels in a University Hospital in the Eastern Province of Saudi Arabia,” J Family Community Med, vol. 21, no. 1, pp. 39–47, Apr. 2014, doi: 10.4103/2230-8229.128778.
M. N. N. Rodrigo, Y. Kosala, B. A. K. S. Perera, and C. Dalugoda, “Mitigation of Hospital Acquired Infections in Developing Countries through the Provision of a Better IAQ,” Engineer: Journal of the Institution of Engineers, Sri Lanka, vol. 51, no. 1, p. 39, Jan. 2018, doi: 10.4038/ENGINEER.V51I1.7286.
U. M. Hellgren, M. Hyvärinen, R. Holopainen, and K. Reijula, “Perceived indoor air quality, air- related symptoms and ventilation in Finnish hospitals,” Int J Occup Med Environ Health, vol. 24, no. 1, pp. 48–56, 2011, doi: 10.2478/S13382-011-0011-5.
S. K. Koutroumpi, “Identifying Gap of Knowledge about Thermal Comfort in Naturally Ventilated Wards in Hot-humid Settings,” Global Journal of Engineering Sciences, vol. 6, no. 2, Jul. 2020, doi: 10.33552/GJES.2020.06.000632.
K. Chaloeytoy, A. Dubsok, and S. Kittipongvises, “Evaluating Thermal Comfort in Ward Areas of the Public Hospital in the Tropical Climates,” E3S Web of Conferences, vol. 530, May 2024, doi: 10.1051/E3SCONF/202453005009.
L. Faraj, M. F. Z. Bin Jaafar, and Z. Shari, “Evaluating Ventilation for Thermal Comfort in Two Classrooms Types in Malaysian Secondary Classrooms,” International Journal of Sustainable Development and Planning, vol. 18, no. 7, pp. 2069–2078, Jul. 2023, doi: 10.18280/IJSDP.180709.
K. T. Huang and R. L. Hwang, “Parametric study on energy and thermal performance of school buildings with natural ventilation, hybrid ventilation and air conditioning,” Indoor and Built Environment, vol. 25, no. 7, pp. 1148– 1162, Nov. 2016, doi: 10.1177/1420326X15609773.
F. Azizpour, S. Moghimi, E. Salleh, S. Mat, C. H. Lim, and K. Sopian, “Thermal comfort assessment of large-scale hospitals in tropical climates: A case study of University Kebangsaan Malaysia Medical Centre (UKMMC),” Energy Build, vol. 64, pp. 317–322, 2013, doi: 10.1016/J.ENBUILD.2013.05.033.
D. Palladino, I. Nardi, and C. Buratti, “Artificial Neural Network for the Thermal Comfort Index Prediction: Development of a New Simplified Algorithm,” Energies (Basel), vol. 13, no. 17, Sep. 2020, doi: 10.3390/EN13174500.
G. Tardioli, R. Filho, P. Bernaud, and D. Ntimos, “An Innovative Modelling Approach Based on Building Physics and Machine Learning for the Prediction of Indoor Thermal Comfort in an Office Building,” Buildings, vol. 12, no. 4, Apr. 2022, doi: 10.3390/BUILDINGS12040475.
A. De et al., “Implementing At-Scale Adaptive Thermal Comfort Controls for Mixed Mode Building Using Machine Learning,” FARU Journal, vol. 9, no. 2, pp. 12–19, Dec. 2022, doi: 10.4038/FARUJ.V9I2.172.
Y. J. Ju, J. R. Lim, and E. S. Jeon, “Prediction of AI- Based Personal Thermal Comfort in a Car Using Machine-Learning Algorithm,” Electronics (Basel), vol. 11, no. 3, Feb. 2022, doi: 10.3390/ELECTRONICS11030340.
S. Liu, S. Schiavon, H. P. Das, M. Jin, and C. J. Spanos, “Personal thermal comfort models with wearable sensors,” Build Environ, vol. 162, Sep. 2019, doi: 10.1016/J.BUILDENV.2019.106281.
M. Nascimento and P. Lopes, “Internet of things and machine learning applied to the thermal comfort of internal environments,” Indoor and Built Environment, vol. 31, no. 9, pp. 2274–2290, Nov. 2022, doi: 10.1177/1420326X221097338.
L. T. Wong, K. W. Mui, and T. W. Tsang, “Updating Indoor Air Quality (IAQ) Assessment Screening Levels with Machine Learning Models,” Int J Environ Res Public Health, vol. 19, no. 9, May 2022, doi: 10.3390/IJERPH19095724.
K. Huang, S. Lu, X. Li, and W. Chen, “Using random forests to predict passengers’ thermal comfort in underground train carriages,” Indoor and Built Environment, vol. 32, no. 2, 2022, doi: 10.1177/1420326X221110046.
How to cite this article
Razak, T.R., Ismail, M.H., Jarimi, H., Nadzir, M.S.M., Zheng, T., Yanan, Z., Ahmad, E.Z., Syafiq, U., Ludin, N.A., Rahman, N.M.A., Jamaludin, M.H. and Riffat, S. (2025). 'Machine Learning-Based Predictive Models for Indoor Air Quality and Thermal Comfort: Bridging Sensor Data and Human Perception in Healthcare Facilities'. Energy Catalyst, 1, pp. 35-53. https://doi.org/10.61552/EC.2025.003
Check for updates