Document is current

Article History

Received: 7 June 2026

Accepted: 18 September 2026

First Online: 24 September 2026

Declarations

Competing interests: The authors declare no competing interests.

Ethics approval and consent to participate: This engineering study examined building physics and AI-based control and involved no clinical intervention or physiological measurement. Occupancy data comprised voluntary, anonymized, and aggregated presence indicators. Under institutional guidelines, this non-interventional engineering data collection did not require formal ethics-committee approval. Nevertheless, all household residents and business operators provided written informed consent before sensor installation. The consent statement described the collected data, including load signatures, door-contact events, and CO₂ concentration, and their use in developing and validating the control framework. Identifiers were replaced with study codes during data ingestion. The site coordination team stored the address-code mapping separately, and it was inaccessible to the model-development team. Participants could withdraw without consequences for tenancy or business operation. Raw sensor data will be retained for five years after study completion and then deleted according to schedule. All procedures followed the applicable privacy and confidentiality principles of the Declaration of Helsinki.

Declaration of generative AI and AI-assisted technologies: During the preparation of this manuscript, the authors used ChatGPT (OpenAI) to improve the language and readability of the text, and to assist in refining the visual styling of figures generated with Python (Matplotlib, Seaborn, and Plotly). All data, results, and scientific content were produced and verified solely by the authors, who reviewed and edited the AI-assisted output and take full responsibility for the published article.