Intelligent Comfort Management in Classrooms Using SSD-Based Occupant Detection and PMV-Guided Environmental Control

Al Barra  Harahap; Vera Khoirunisa; Berton Charisdito  Hutahaean; Donni Marulitua  Tarigan; Sefrani I.G Siregar; Hasanah Pratiwi Harahap

doi:10.5614/joki.2025.17.2.9

Authors

Al Barra Harahap Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Sumatera, 35365, Lampung, Indonesia
Vera Khoirunisa Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Sumatera, 35365, Lampung, Indonesia
Berton Charisdito Hutahaean Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Sumatera, 35365, Lampung, Indonesia
Donni Marulitua Tarigan Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Sumatera, 35365, Lampung, Indonesia
Sefrani I.G Siregar Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Sumatera, 35365, Lampung, Indonesia
Hasanah Pratiwi Harahap Diploma IV in Midwifery, Faculty of Pharmacy and Health Sciences, Institut Kesehatan Helvetia Medan, 20124, Deli Serdang, Indonesia

Keywords:

Room comfort, Control, PMV, SNI, SSD, NVIDIA Jetson Nano

Abstract

Room comfort is critical for enhancing productivity, particularly in classrooms. Two key factors are temperature and lighting, governed by ASHRAE 55 for thermal comfort (PMV range of –0.5 to 0.5) and SNI 6197:2020 for classroom lighting (350 lux). This study develops an intelligent system that coordinates occupant detection with temperature and lighting control. Occupant detection was implemented using the Single Shot MultiBox Detector (SSD) with MobileNetV2, a camera as the sensor, and image processing on an NVIDIA Jetson Nano. The detected occupant coordinates were used to control lighting patterns, while temperature was measured with a DHT22 sensor and regulated through PMV-based calculations. The recommended temperature setpoints were transmitted to an air conditioner via an IR blaster controlled by an ESP8266. Experimental results show that the detection system achieved 95% accuracy, 99% precision, 95% recall, and a 97% F1-score at a threshold of 0.3. The lighting control system achieved a MAPE of 14.49%, while the temperature control system achieved a MAPE of 4.53% with an average MAE of 1.1 °C. These findings demonstrate that the proposed system effectively integrates occupant detection with automated temperature and lighting control, ensuring improved classroom comfort.

Author Biographies

Vera Khoirunisa, Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Sumatera, 35365, Lampung, Indonesia

Department of Engineering Physics

Sefrani I.G Siregar, Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Sumatera, 35365, Lampung, Indonesia

Department of Engineering Physics

References

Z. S. Zomorodian, M. Tahsildoost, and M. Hafezi, "Thermal comfort in educational buildings: A review article," Renew. Sustain. Energy Rev., vol. 59, pp. 895–906, 2016, doi: https://doi.org/10.1016/j.rser.2016.01.033.

P. Bluyssen, The Indoor Environment Handbook: How to Make Buildings Healthy and Comfortable. London : U.K.: Routledge, 2009, doi: https://doi.org/10.4324/9781849774611.

C. Barkmann, N. Wessolowski, and M. Schulte-Markwort, "Applicability and efficacy of variable light in schools," Physiol. Behav., vol. 105, no. 3, pp. 621–627, 2012, doi: https://doi.org/10.1016/j.physbeh.2011.09.020.

C.-P. Chen, R.-L. Hwang, W. Liu, W.-M. Shih, and S.-Y. Chang, "The influence of air-conditioning managerial scheme in hybrid-ventilated classrooms on students’ thermal perception," Indoor Built Environ., vol. 24, no. 6, pp. 761–770, 2015, doi: https://doi.org/10.1177/1420326X14530587.

Thermal Environmental Conditions for Human Occupancy, ANSI/ASHRAE Standard 55-2017, ASHRAE, . Atlanta, GA, USA, 2017.

H.-S. Lee, S.-Y. Kwon, and J.-H. Lim, "A development of a lighting control system based on context-awareness for the improvement of learning efficiency in classroom," Wireless Pers. Commun., vol. 86, pp. 165–181, 2016, doi: https://doi.org/10.1007/s11277-015-2811-6.

R. Golmohammadi, H. Yousefi, N. S. Khotbesara, A. Nasrolahi, and N. Kurd, "Effects of light on attention and reaction time: A systematic review," J. Res. Health Sci., vol. 21, no. 2, pp. 1–8, Mar. 2021, doi: https://doi.org/10.34172/jrhs.2021.66.

Y. Sun, Z. Zhang, and J. Zhang, "Improving indoor thermal comfort and air-conditioning management in primary school classrooms," Processes, vol. 13, no. 5, art. 1538, 2025, doi: https://doi.org/10.3390/pr13051538.

V. P. Widartha, I. Ra, S.-Y. Lee, and C.-S. Kim, "Advancing smart lighting: A developmental approach to energy efficiency through brightness adjustment strategies," J. Low Power Electron. Appl., vol. 14, no. 1, art. 6, 2024, doi: https://doi.org/10.3390/jlpea14010006.

H. Zahid, O. Elmansoury, and R. Yaagoubi, "Dynamic predicted mean vote: An IoT-BIM integrated approach for indoor thermal comfort optimization," Autom. Constr., vol. 129, art. 103805, 2021, doi: https://doi.org/10.1016/j.autcon.2021.103805.

Y.-C. Chiu, C.-Y. Tsai, M.-D. Ruan, G.-Y. Shen, and T.-T. Lee, "MobileNet-SSDv2: An improved object detection model for embedded systems," in Proc. Int. Conf. System Science and Engineering (ICSSE), pp. 1–5, 2020, doi: https://doi.org/10.1109/ICSSE50014.2020.9219319.

P. Mittal, "A comprehensive survey of deep learning-based lightweight object detection models for edge devices," Artif. Intell. Rev., vol. 57, art. 242, 2024, doi: https://doi.org/10.1007/s10462-024-10877-1.

W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, "SSD: Single shot multibox detector," in Proc. Eur. Conf. Comput. Vis. (ECCV), Amsterdam, The Netherlands, pp. 21–37, 2016, doi: https://doi.org/10.48550/arXiv.1512.02325.

S. W. Keckler, W. J. Dally, B. Khailany, M. Garland, and D. Glasco, "GPUs and the future of parallel computing," IEEE Micro, vol. 31, no. 5, pp. 7–17, 2011, doi : https://doi.org/10.1109/MM.2011.89 .

Espressif Systems, ESP8266EX datasheet. (2020) Accessed : 1 August 2025 [Online]. Available: https://www.espressif.com/en/products/socs/esp8266.

M. A. Ajis, "Otomasi intensitas cahaya ruangan berdasarkan aktivitas manusia dengan menggunakan algoritma OpenPose," Undergraduate thesis, Institut Teknologi Sumatera, Lampung, Indonesia, 2024, [Online]. Available: https://repo.itera.ac.id/depan/submission/SB2401160040.

Z. Zhang, "Indoor room occupancy counting based on LSTM and environmental sensor," Dec. 2022, arXiv preprint, arXiv:2212.02364, doi: https://doi.org/10.48550/arXiv.2212.02364.