Cross-room CO2-based presence detection for occupancy profiling
- Author
- Jelle Vanhaeverbeke (UGent) , Emiel Deprost (UGent) , Steven Verstockt (UGent) and Sofie Van Hoecke (UGent)
- Organization
- Project
- Abstract
- Control systems for building services, such as heating and cooling, often rely on fixed timing schemes. While such approaches are convenient, they make strong assumptions about room usage, often leading to inadequate comfort and energy efficiency. This study addresses this limitation by presenting two contributions aimed at automating the configuration of building control systems. The first contribution involves the development of a presence detection model based on CO2 data, which is easy to measure and non-privacy intrusive. Unlike existing literature, which typically focuses on single-room applications, this work introduces a dataset and machine learning methodology demonstrating the generalizability of a presence detection model across various real-world rooms, even among different building types. Sliding window normalization of the sensor data is the key to achieve this unsupervised cross-room adaptability. As second contribution, we propose an occupancy profiling technique that relies on the predicted presence information. This approach facilitates the automated configuration of building control systems by using historical presence probabilities to anticipate future occupancy. In contrast to fixed timing schemes, these occupancy profiles dynamically adapt over time, accommodating changes in occupant behavior. As such, this work improves the configuration of building control systems, leading to a more comfortable and energy-efficient environment.
- Keywords
- Adaptation models, Mathematical models, Buildings, Hidden Markov models, Schedules, Heating systems, Data models, Control systems, Accuracy, Ventilation, Building control, CO2, occupancy profiling, presence detection
Downloads
-
DS928.pdf
- full text (Published version)
- |
- open access
- |
- |
- 1.12 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01K1AW3YDJQWYAS4V6TEGTFYYH
- MLA
- Vanhaeverbeke, Jelle, et al. “Cross-Room CO2-Based Presence Detection for Occupancy Profiling.” IEEE ACCESS, vol. 13, IEEE, 2025, pp. 120917–30, doi:10.1109/ACCESS.2025.3588031.
- APA
- Vanhaeverbeke, J., Deprost, E., Verstockt, S., & Van Hoecke, S. (2025). Cross-room CO2-based presence detection for occupancy profiling. IEEE ACCESS, 13, 120917–120930. https://doi.org/10.1109/ACCESS.2025.3588031
- Chicago author-date
- Vanhaeverbeke, Jelle, Emiel Deprost, Steven Verstockt, and Sofie Van Hoecke. 2025. “Cross-Room CO2-Based Presence Detection for Occupancy Profiling.” IEEE ACCESS 13: 120917–30. https://doi.org/10.1109/ACCESS.2025.3588031.
- Chicago author-date (all authors)
- Vanhaeverbeke, Jelle, Emiel Deprost, Steven Verstockt, and Sofie Van Hoecke. 2025. “Cross-Room CO2-Based Presence Detection for Occupancy Profiling.” IEEE ACCESS 13: 120917–120930. doi:10.1109/ACCESS.2025.3588031.
- Vancouver
- 1.Vanhaeverbeke J, Deprost E, Verstockt S, Van Hoecke S. Cross-room CO2-based presence detection for occupancy profiling. IEEE ACCESS. 2025;13:120917–30.
- IEEE
- [1]J. Vanhaeverbeke, E. Deprost, S. Verstockt, and S. Van Hoecke, “Cross-room CO2-based presence detection for occupancy profiling,” IEEE ACCESS, vol. 13, pp. 120917–120930, 2025.
@article{01K1AW3YDJQWYAS4V6TEGTFYYH,
abstract = {{Control systems for building services, such as heating and cooling, often rely on fixed timing schemes. While such approaches are convenient, they make strong assumptions about room usage, often leading to inadequate comfort and energy efficiency. This study addresses this limitation by presenting two contributions aimed at automating the configuration of building control systems. The first contribution involves the development of a presence detection model based on CO2 data, which is easy to measure and non-privacy intrusive. Unlike existing literature, which typically focuses on single-room applications, this work introduces a dataset and machine learning methodology demonstrating the generalizability of a presence detection model across various real-world rooms, even among different building types. Sliding window normalization of the sensor data is the key to achieve this unsupervised cross-room adaptability. As second contribution, we propose an occupancy profiling technique that relies on the predicted presence information. This approach facilitates the automated configuration of building control systems by using historical presence probabilities to anticipate future occupancy. In contrast to fixed timing schemes, these occupancy profiles dynamically adapt over time, accommodating changes in occupant behavior. As such, this work improves the configuration of building control systems, leading to a more comfortable and energy-efficient environment.}},
author = {{Vanhaeverbeke, Jelle and Deprost, Emiel and Verstockt, Steven and Van Hoecke, Sofie}},
issn = {{2169-3536}},
journal = {{IEEE ACCESS}},
keywords = {{Adaptation models,Mathematical models,Buildings,Hidden Markov models,Schedules,Heating systems,Data models,Control systems,Accuracy,Ventilation,Building control,CO2,occupancy profiling,presence detection}},
language = {{eng}},
pages = {{120917--120930}},
publisher = {{IEEE}},
title = {{Cross-room CO2-based presence detection for occupancy profiling}},
url = {{http://doi.org/10.1109/ACCESS.2025.3588031}},
volume = {{13}},
year = {{2025}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: