Machine Learning Model Evaluation for Predicting Damper Control to Regulate Temperature in Isolation Room

Abstract:

Isolation rooms prevent the spread of airborne diseases from infected people to others. These rooms have a system that keeps them clean by managing the air circulation, temperature, and humidity. This study creates a prediction model for an automated control system that adjusts the temperature in an isolation room by modifying the air supply with a damper. The control system relies on a machine learning model that uses sensor readings data as inputs and damper output data as outputs to change the airflow to the isolation room with a data collection using a closed loop algorithm control system. The data from the experiment are used to train and test different machine learning models such as K-Nearest Neighbour (KNN), Random Forest, Logistic Regression, Decision Tree, and Support vector machine (SVM). The performance of the damper control prediction is assessed by accuracy, recall, F1 score, and Receiver Operating Characteristic (ROC) / Area Under Curve (AUC). In this study, the KNN model performs best with accuracy, recall, and F1 score values of 0.84, 0.95, and 0.81, respectively.

• Periodical: Defect and Diffusion Forum (Volume 442)
• Pages: 55-62
• DOI: https://doi.org/10.4028/p-RZm2Qd
• Online since: May 2025
• Authors: Muhammad Salamul Fajar Sabri, Samsul Rizal, Rudi Kurniawan*, Taufik Fuadi Abidin, Zahrul Fuadi, Razali Thaib
• Keywords: Control System, Damper Control, HVAC, Isolation Room, Machine Learning

References

[1] M. Moghadami, "A narrative review of influenza: A seasonal and pandemic disease," Iran. J. Med. Sci., vol. 42, no. 1, p.2–13, 2017.

[2] M. Pai et al., "Tuberculosis," Nat. Rev. Dis. Prim., vol. 2, 2016.

DOI: 10.1038/nrdp.2016.76

[3] E. Schneider, "Severe Acute Respiratory Syndrome (SARS)," Netter's Infect. Dis., p.537–543, 2012.

DOI: 10.1016/B978-1-4377-0126-5.00089-6

[4] A. A. Gershon et al., "Varicella zoster virus infection," Nat. Rev. Dis. Prim., vol. 1, p.1–41, 2015.

DOI: 10.1038/nrdp.2015.16

[5] L. Borro, L. Mazzei, M. Raponi, P. Piscitelli, A. Miani, and A. Secinaro, "The role of air conditioning in the diffusion of Sars-CoV-2 in indoor environments: A first computational fluid dynamic model, based on investigations performed at the Vatican State Children's hospital," Environ. Res., vol. 193, Feb. 2021.

DOI: 10.1016/j.envres.2020.110343

[6] P. Bahl, C. Doolan, C. De Silva, A. A. Chughtai, L. Bourouiba, and C. R. Macintyre, "Airborne or Droplet Precautions for Health Workers Treating Coronavirus Disease 2019 ?," no. Xx Xxxx, p.1–8, 2020.

DOI: 10.1093/infdis/jiaa189

[7] P. E. Valenzuela, A. Ebadat, N. Everitt, and A. Parisio, "Closed-loop identification for model predictive control of HVAC systems: From input design to controller synthesis," IEEE Trans. Control Syst. Technol., vol. 28, no. 5, p.1681–1695, 2020.

DOI: 10.1109/TCST.2019.2917675

[8] A. Sporr, G. Zucker, and R. Hofmann, "Automated HVAC Control Creation Based on Building Information Modeling (BIM): Ventilation System," IEEE Access, vol. 7, p.74747–74758, 2019.

DOI: 10.1109/ACCESS.2019.2919262

[9] C. Anuntasethakul and D. Banjerdpongchai, "Design of Supervisory Model Predictive Control for Building HVAC System with Consideration of Peak-Load Shaving and Thermal Comfort," IEEE Access, vol. 9, p.41066–41081, 2021.

DOI: 10.1109/ACCESS.2021.3065083

[10] S. Jacob, S. S. Yadav, and B. S. Sikarwar, Design and simulation of isolation room for a hospital, no. August 2020. Springer Singapore, 2019.

DOI: 10.1007/978-981-13-6416-7_8

[11] European Centre for Disease Prevention and Controls, "Heating, Ventilation and Air-Conditioning Systems In The Context of COVID-19," Eur. Cent. Dis. Prev. Control., no. June, p.1–5, 2020, [Online]. Available: https://www.ecdc.europa.eu/sites/default/ files/documents/Ventilation-in-the-context-of-COVID-19.pdf

[12] K. Khankari, "Patient Room HVAC," ASHRAE J., vol. 58, no. 6, p.16–26, 2016.

[13] F. Wang, C. Chaerasari, D. Rakshit, I. Permana, and Kusnandar, "Performance improvement of a negative-pressurized isolation room for infection control," Healthc., vol. 9, no. 8, p.1–11, 2021.

DOI: 10.3390/healthcare9081081

[14] S. Bhattacharyya, K. Dey, A. R. Paul, and R. Biswas, "A novel CFD analysis to minimize the spread of COVID-19 virus in hospital isolation room," Chaos, Solitons and Fractals, vol. 139, p.110294, 2020.

DOI: 10.1016/j.chaos.2020.110294

[15] H. Hamdani et al., "HVAC Control Systems for a Negative Air Pressure Isolation Room and Its Performance," Sustainability, vol. 14, no. 18, p.11537, 2022.

DOI: 10.3390/su141811537

[16] D. Borda, M. Bergagio, M. Amerio, M. C. Masoero, R. Borchiellini, and D. Papurello, "Development of Anomaly Detectors for HVAC Systems Using Machine Learning," Processes, vol. 11, no. 2, p.1–26, 2023.

DOI: 10.3390/pr11020535

[17] G. Demirezen, A. S. Fung, and M. Deprez, "Development and optimization of artificial neural network algorithms for the prediction of building specific local temperature for HVAC control," Int. J. Energy Res., vol. 44, no. 11, p.8513–8531, 2020.

DOI: 10.1002/er.5537

[18] C. L. Weng and L. J. Kau, "Planning and design of a full-outer-air-intake natural air-conditioning system for medical negative pressure isolation wards," J. Healthc. Eng., vol. 2021, 2021.

DOI: 10.1155/2021/8872167

[19] S. Saran et al., "Heating, ventilation and air conditioning (HVAC) in intensive care unit," Crit. Care, vol. 24, no. 1, p.1–11, 2020.

DOI: 10.1186/s13054-020-02907-5

[20] W. Zheng et al., "COVID-19 Impact on Operation and Energy Consumption of Heating, Ventilation and Air-Conditioning (HVAC) Systems," Adv. Appl. Energy, vol. 3, no. May, p.100040, 2021.

DOI: 10.1016/j.adapen.2021.100040

[21] T. Thermometry and G. Usage, "Guide to Secondary Thermometry," p.1–62, 2021.

[22] E. Webster, "A critical review of the common thermocouple reference functions," Metrologia, vol. 58, no. 2, 2021.

DOI: 10.1088/1681-7575/abdd9a

[23] H. I. Inc., Non-Spring Return Direct-Coupled Damper Actuators for Contents of Package. 1985.

[24] G. Prytz, "A performance analysis of EtherCAT and PROFINET IRT," IEEE Int. Conf. Emerg. Technol. Fact. Autom. ETFA, no. 1396, p.408–415, 2008.

DOI: 10.1109/ETFA.2008.4638425

[25] G. Cena, I. C. Bertolotti, S. Scanzio, A. Valenzano, and C. Zunino, "Evaluation of EtherCAT distributed clock performance," IEEE Trans. Ind. Informatics, vol. 8, no. 1, p.20–29, 2012.

DOI: 10.1109/TII.2011.2172434

[26] M. Esrafilian-Najafabadi and F. Haghighat, "Impact of occupancy prediction models on building HVAC control system performance: Application of machine learning techniques," Energy Build., vol. 257, p.111808, 2022.

DOI: 10.1016/j.enbuild.2021.111808

[27] A. Al Mohammad, H. Hirmiz, G. Perera, and M. Maleki, "Motif-Based Occupancy Prediction for Energy Efficiency in HVAC," 2022 3rd Int. Conf. Pattern Recognit. Mach. Learn. PRML 2022, p.465–469, 2022.

DOI: 10.1109/PRML56267.2022.9882198

[28] S. Faddel, G. Tian, Q. Zhou, and H. Aburub, "On the Performance of Data-Driven Reinforcement Learning for Commercial HVAC Control," 2020 IEEE Ind. Appl. Soc. Annu. Meet. IAS 2020, 2020.

DOI: 10.1109/IAS44978.2020.9334865

[29] I. A. Rauf, "Basics of Machine Learning," Phys. Data Sci. Mach. Learn., no. May, p.125–155, 2021.

DOI: 10.1201/9781003206743-6