{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:50:48Z","timestamp":1792785048743,"version":"4.5.0"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"vor","delay-in-days":96,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Hangzhou Joint Fund of the Zhejiang Provincial Natural Science Foundation of China","award":["LHZY24A010004"],"award-info":[{"award-number":["LHZY24A010004"]}],"id":[{"id":"https:\/\/ror.org\/04aqat463","id-type":"ROR","asserted-by":"crossref"}]},{"name":"the 2025 Research Cultivation Plan Project of Hangzhou City University","award":["J-202514"],"award-info":[{"award-number":["J-202514"]}],"id":[{"id":"https:\/\/ror.org\/01wck0s05","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurate identification of indoor occupant presence is crucial for intelligent building energy management. Traditional monitoring methods are often invasive and lack standardized quantitative indicators. Therefore, this study proposes a non-invasive occupant presence state prediction method based on machine learning. Six machine learning algorithms\u2014Logistic Regression, Decision Tree, k-Nearest Neighbor (KNN), Random Forest, CatBoost, and XGBoost\u2014were evaluated across five building scenarios (hospitals, classrooms, dormitories, offices, and dwelling houses) using core environmental features including air temperature, relative humidity, sound pressure level, illuminance, CO\n                    <jats:sub>2<\/jats:sub>\n                    concentration, formaldehyde (HCHO), PM\n                    <jats:sub>2.5<\/jats:sub>\n                    , PM\n                    <jats:sub>1.0<\/jats:sub>\n                    , and PM\n                    <jats:sub>10<\/jats:sub>\n                    . A temporally ordered walk-forward evaluation framework was adopted to prevent data leakage, with VIF screening and RFECV for feature selection. The best-performing models achieved mean accuracies ranging from 0.61 (dwelling) to 0.88 (office), with the optimal algorithm varying by scenario. SHAP-based interpretability analysis identified CO\n                    <jats:sub>2<\/jats:sub>\n                    concentration, illuminance as the most consistently influential predictors, with PM\n                    <jats:sub>2.5<\/jats:sub>\n                    , temperature, and sound contributing in scenario-specific patterns. A leave-one-feature-out sensitivity analysis showed that removing CO\n                    <jats:sub>2<\/jats:sub>\n                    caused the largest performance drop in the hospital scenario. This study provides a comparative analysis of explainable machine-learning predictors across five single-room building scenarios under a temporally aligned protocol, providing comparative observations that may inform subsequent multi-room and closed-loop studies of smart building management.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-59912-x","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:23:43Z","timestamp":1783700623000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-scenario evaluation of explainable machine learning for non-invasive summer occupancy detection across five building scenarios"],"prefix":"10.1038","volume":"16","author":[{"given":"Jiantao","family":"Weng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhitong","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingqi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xihao","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jindong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Ying","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"59912_CR1","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.enbuild.2016.06.089","volume":"128","author":"X Cao","year":"2016","unstructured":"Cao, X., Dai, X. & Liu, J. Building energy-consumption status worldwide and the state-of-the-art technologies for zero-energy buildings during the past decade. Energy Build. 128, 198\u2013213. https:\/\/doi.org\/10.1016\/j.enbuild.2016.06.089 (2016).","journal-title":"Energy Build."},{"key":"59912_CR2","unstructured":"U.S. Department of Energy, An assessment of energy technologies and research opportunities, Chapter 5, 2015."},{"key":"59912_CR3","doi-asserted-by":"publisher","first-page":"102725","DOI":"10.1016\/j.jobe.2021.102725","volume":"43","author":"P Jafarpur","year":"2021","unstructured":"Jafarpur, P. & Berardi, U. Effects of climate changes on building energy demand and thermal comfort in Canadian office buildings adopting different temperature setpoints. J. Build. Eng. 43, 102725 (2021).","journal-title":"J. Build. Eng."},{"issue":"6","key":"59912_CR4","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1016\/S0378-7788(02)00167-6","volume":"35","author":"A Al-Mumin","year":"2003","unstructured":"Al-Mumin, A., Khattab, O. & Sridhar, G. Occupants\u2019 behavior and activity patterns influencing the energy consumption in the Kuwaiti residences. Energy Build. 35(6), 549\u2013559. https:\/\/doi.org\/10.1016\/S0378-7788(02)00167-6 (2003).","journal-title":"Energy Build."},{"key":"59912_CR5","doi-asserted-by":"publisher","first-page":"111657","DOI":"10.1016\/j.enbuild.2021.111657","volume":"255","author":"M Laskari","year":"2022","unstructured":"Laskari, M., Masi, R., Karatasou, S., Santamouris, M. & Assimakopoulos, M. On the impact of user behavior on heating energy consumption and indoor temperature in residential buildings. Energy Build. 255, 111657. https:\/\/doi.org\/10.1016\/j.enbuild.2021.111657 (2022).","journal-title":"Energy Build."},{"key":"59912_CR6","doi-asserted-by":"publisher","first-page":"2090","DOI":"10.1016\/j.egyr.2024.01.075","volume":"11","author":"S Lee","year":"2024","unstructured":"Lee, S., Oh, S. & Lim, J. Lighting control method based on RIIL to reduce building energy consumption. Energy Rep. 11, 2090\u20132098. https:\/\/doi.org\/10.1016\/j.egyr.2024.01.075 (2024).","journal-title":"Energy Rep."},{"key":"59912_CR7","doi-asserted-by":"publisher","first-page":"108524","DOI":"10.1016\/j.buildenv.2021.108524","volume":"207","author":"Y Yang","year":"2022","unstructured":"Yang, Y., Yuan, Y., Pan, T., Zang, X. & Liu, G. A framework for occupancy prediction based on image information fusion and machine learning. Build. Environ. 207, 108524 (2022).","journal-title":"Build. Environ."},{"key":"59912_CR8","doi-asserted-by":"publisher","first-page":"114284","DOI":"10.1016\/j.rser.2024.114284","volume":"193","author":"T Li","year":"2024","unstructured":"Li, T. et al. A systematic review and comprehensive analysis of building occupancy prediction. Renew. Sustain. Energy Rev. 193, 114284 (2024).","journal-title":"Renew. Sustain. Energy Rev."},{"key":"59912_CR9","doi-asserted-by":"publisher","first-page":"121594","DOI":"10.1016\/j.apenergy.2023.121594","volume":"349","author":"Z Pang","year":"2023","unstructured":"Pang, Z. et al. Adopting occupancy-based HVAC controls in commercial building energy codes: Analysis of cost-effectiveness and decarbonization potential. Appl. Energy 349, 121594 (2023).","journal-title":"Appl. Energy"},{"key":"59912_CR10","doi-asserted-by":"publisher","first-page":"116326","DOI":"10.1016\/j.enbuild.2025.116326","volume":"347","author":"X Liu","year":"2025","unstructured":"Liu, X., Chen, X., Zhang, J. & Liu, L. Optimizing HVAC performance through occupancy-based control: A machine learning approach for energy efficiency and comfort. Energy Build. 347, 116326 (2025).","journal-title":"Energy Build."},{"key":"59912_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2025.113714","author":"S Babosalam","year":"2025","unstructured":"Babosalam, S., Kargar, S. M., Moazzami, M. & Zanjani, S. M. Occupancy-aware energy optimization in building-to-grid systems using deep neural networks and model predictive control. J. Build. Eng. https:\/\/doi.org\/10.1016\/j.jobe.2025.113714 (2025).","journal-title":"J. Build. Eng."},{"key":"59912_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2025.113716","author":"X Zhang","year":"2025","unstructured":"Zhang, X., Dunn, S., Luo, Y. & Shen, Y. Integrating human behaviors in an agent-based model for multi-floor building emergency evacuation. J. Build. Eng. https:\/\/doi.org\/10.1016\/j.jobe.2025.113716 (2025).","journal-title":"J. Build. Eng."},{"key":"59912_CR13","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1016\/j.aej.2024.01.030","volume":"91","author":"L Zhang","year":"2024","unstructured":"Zhang, L. et al. A multi-channel hybrid deep learning framework for multi-sensor fusion enabled human activity recognition. Alexandria Eng. J. 91, 472\u2013485. https:\/\/doi.org\/10.1016\/j.aej.2024.01.030 (2024).","journal-title":"Alexandria Eng. J."},{"key":"59912_CR14","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1016\/j.aej.2023.09.013","volume":"80","author":"S Jameer","year":"2023","unstructured":"Jameer, S. & Syed, H. A DCNN-LSTM based human activity recognition by mobile and wearable sensor networks. Alex. Eng. J. 80, 542\u2013552. https:\/\/doi.org\/10.1016\/j.aej.2023.09.013 (2023).","journal-title":"Alex. Eng. J."},{"key":"59912_CR15","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1016\/j.aej.2023.05.050","volume":"74","author":"A Hussain","year":"2023","unstructured":"Hussain, A. et al. Low-light aware framework for human activity recognition via optimized dual stream parallel network. Alex. Eng. J. 74, 569\u2013583. https:\/\/doi.org\/10.1016\/j.aej.2023.05.050 (2023).","journal-title":"Alex. Eng. J."},{"issue":"2","key":"59912_CR16","doi-asserted-by":"publisher","first-page":"332","DOI":"10.3390\/s18020332","volume":"18","author":"D Yang","year":"2018","unstructured":"Yang, D. et al. Passive infrared (PIR)-based indoor position tracking for smart homes using accessibility maps and A-star algorithm. Sensors 18(2), 332. https:\/\/doi.org\/10.3390\/s18020332 (2018).","journal-title":"Sensors"},{"issue":"9","key":"59912_CR17","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.3785\/j.issn.1008-973X.2020.09.003","volume":"54","author":"X Li","year":"2020","unstructured":"Li, X. et al. Analysis of air-conditioning use and energy consumption in university teaching buildings with data mining. J. Zhejiang Univ. (Eng. Sci.) 54(9), 1677\u20131689. https:\/\/doi.org\/10.3785\/j.issn.1008-973X.2020.09.003 (2020).","journal-title":"J. Zhejiang Univ. (Eng. Sci.)"},{"issue":"2","key":"59912_CR18","doi-asserted-by":"publisher","first-page":"3036","DOI":"10.1109\/JSYST.2022.3140546","volume":"16","author":"C Yu","year":"2022","unstructured":"Yu, C. et al. Noninvasive human activity recognition using millimeter-wave radar. IEEE Syst. J. 16(2), 3036\u20133047. https:\/\/doi.org\/10.1109\/JSYST.2022.3140546 (2022).","journal-title":"IEEE Syst. J."},{"key":"59912_CR19","doi-asserted-by":"publisher","first-page":"111593","DOI":"10.1016\/j.enbuild.2021.111593","volume":"254","author":"K Sun","year":"2022","unstructured":"Sun, K. et al. Indoor occupancy measurement by the fusion of motion detection and static estimation. Energy Build. 254, 111593. https:\/\/doi.org\/10.1016\/j.enbuild.2021.111593 (2022).","journal-title":"Energy Build."},{"key":"59912_CR20","doi-asserted-by":"publisher","first-page":"108812","DOI":"10.1016\/j.buildenv.2022.108812","volume":"212","author":"B Pollard","year":"2022","unstructured":"Pollard, B. et al. Associations between spatial attributes, IEQ exposures and occupant movement behavior in an open-plan office. Build. Environ. 212, 108812. https:\/\/doi.org\/10.1016\/j.buildenv.2022.108812 (2022).","journal-title":"Build. Environ."},{"key":"59912_CR21","doi-asserted-by":"publisher","first-page":"110863","DOI":"10.1016\/j.enbuild.2021.110863","volume":"242","author":"S Kampezidou","year":"2021","unstructured":"Kampezidou, S. et al. Real-time occupancy detection with physics-informed pattern-recognition machines based on limited CO2 and temperature sensors. Energy Build. 242, 110863. https:\/\/doi.org\/10.1016\/j.enbuild.2021.110863 (2021).","journal-title":"Energy Build."},{"key":"59912_CR22","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/8347261","author":"B Fang","year":"2021","unstructured":"Fang, B. et al. Smart bracelet system for temperature monitoring and movement tracking analysis. J. Healthc. Eng. https:\/\/doi.org\/10.1155\/2021\/8347261 (2021).","journal-title":"J. Healthc. Eng."},{"issue":"2","key":"59912_CR23","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s10514-019-09883-y","volume":"44","author":"Z Yan","year":"2020","unstructured":"Yan, Z., Duckett, T. & Bellotto, N. Online learning for 3D LiDAR-based human detection: Experimental analysis of point cloud clustering and classification methods. Auton. Robots 44(2), 147\u2013164. https:\/\/doi.org\/10.1007\/s10514-019-09883-y (2020).","journal-title":"Auton. Robots"},{"issue":"2","key":"59912_CR24","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1109\/JBHI.2019.2907498","volume":"24","author":"J Clemente","year":"2020","unstructured":"Clemente, J. et al. Smart seismic sensing for indoor fall detection, location, and notification. IEEE J. Biomed. Health Inform. 24(2), 524\u2013532. https:\/\/doi.org\/10.1109\/JBHI.2019.2907498 (2020).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"59912_CR25","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.enbuild.2018.04.051","volume":"172","author":"J Yang","year":"2018","unstructured":"Yang, J. et al. Comparison of different occupancy counting methods for single system\u2013single zone applications. Energy Build. 172, 221\u2013234. https:\/\/doi.org\/10.1016\/j.enbuild.2018.04.051 (2018).","journal-title":"Energy Build."},{"issue":"6","key":"59912_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.13614\/j.cnki.11-1962\/tu.2022.06.01","volume":"38","author":"C Li","year":"2022","unstructured":"Li, C. et al. Research on non-invasive office worker rest recognition method based on CO2 concentration and intelligent start\u2013stop strategy of air conditioning. Build. Sci. 38(6), 1\u20137. https:\/\/doi.org\/10.13614\/j.cnki.11-1962\/tu.2022.06.01 (2022).","journal-title":"Build. Sci."},{"key":"59912_CR27","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.buildenv.2016.12.015","volume":"114","author":"Y Wang","year":"2017","unstructured":"Wang, Y. & Shao, L. Understanding occupancy pattern and improving building energy efficiency through Wi-Fi based indoor positioning. Build. Environ. 114, 106\u2013117. https:\/\/doi.org\/10.1016\/j.buildenv.2016.12.015 (2017).","journal-title":"Build. Environ."},{"key":"59912_CR28","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1016\/j.enbuild.2018.03.084","volume":"169","author":"Z Chen","year":"2018","unstructured":"Chen, Z., Jiang, C. & Xie, L. Building occupancy estimation and detection: A review. Energy Build. 169, 260\u2013270. https:\/\/doi.org\/10.1016\/j.enbuild.2018.03.084 (2018).","journal-title":"Energy Build."},{"key":"59912_CR29","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.enbuild.2015.11.071","volume":"112","author":"LM Candanedo","year":"2016","unstructured":"Candanedo, L. M. & Feldheim, V. Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models. Energy Build. 112, 28\u201339. https:\/\/doi.org\/10.1016\/j.enbuild.2015.11.071 (2016).","journal-title":"Energy Build."},{"key":"59912_CR30","unstructured":"E. Hailemariam, R. Goldstein, R. Attar, A. Khan, Real-time occupancy detection using decision trees with multiple sensor types, in: Proceedings of the 2011 Symposium on Simulation for Architecture and Urban Design, Society for Computer Simulation International, San Diego, CA, USA, 2011, pp. 141\u2013148."},{"issue":"10","key":"59912_CR31","doi-asserted-by":"publisher","first-page":"3770","DOI":"10.3390\/s22103770","volume":"22","author":"AR Mena","year":"2022","unstructured":"Mena, A. R., Ceballos, H. G. & Alvarado-Uribe, J. Measuring indoor occupancy through environmental sensors: A systematic review on sensor deployment. Sensors 22(10), 3770 (2022).","journal-title":"Sensors"},{"key":"59912_CR32","doi-asserted-by":"publisher","first-page":"112704","DOI":"10.1016\/j.rser.2022.112704","volume":"167","author":"W Zhang","year":"2022","unstructured":"Zhang, W., Wu, Y. & Calautit, J. K. A review on occupancy prediction through machine learning for enhancing energy efficiency, air quality and thermal comfort in the built environment. Renew. Sustain. Energy Rev. 167, 112704 (2022).","journal-title":"Renew. Sustain. Energy Rev."},{"key":"59912_CR33","doi-asserted-by":"publisher","first-page":"150249","DOI":"10.1016\/j.scitotenv.2021.150249","volume":"804","author":"P Anand","year":"2022","unstructured":"Anand, P., Sekhar, Y., Cheong, J., Santamouris, M. & Kondepudi, S. A review of occupancy-based building energy and IEQ controls and its future post-COVID. Sci. Total Environ. 804, 150249 (2022).","journal-title":"Sci. Total Environ."},{"key":"59912_CR34","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1007\/s12273-021-0861-0","volume":"15","author":"T Yang","year":"2022","unstructured":"Yang, T., Bandyopadhyay, A., O\u2019Neill, Z., Wen, J. & Dong, B. From occupants to occupants: A review of the occupant information understanding for building HVAC occupant-centric control. Build. Simul. 15, 913\u2013932 (2022).","journal-title":"Build. Simul."},{"key":"59912_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.rser.2018.07.019","volume":"96","author":"S Naylor","year":"2018","unstructured":"Naylor, S., Gillott, M. & Lau, T. A review of occupant-centric building control strategies to reduce building energy use. Renew. Sustain. Energy Rev. 96, 1\u201310 (2018).","journal-title":"Renew. Sustain. Energy Rev."},{"key":"59912_CR36","doi-asserted-by":"publisher","first-page":"107810","DOI":"10.1016\/j.buildenv.2021.107810","volume":"197","author":"M Esrafilian-Najafabadi","year":"2021","unstructured":"Esrafilian-Najafabadi, M. & Haghighat, F. Occupancy-based HVAC control systems in buildings: a state-of-the-art review. Build. Environ. 197, 107810 (2021).","journal-title":"Build. Environ."},{"issue":"21","key":"59912_CR37","doi-asserted-by":"publisher","first-page":"14644","DOI":"10.3390\/su142114644","volume":"14","author":"A Mohammadabadi","year":"2022","unstructured":"Mohammadabadi, A., Rahnama, S. & Afshari, A. Indoor occupancy detection based on environmental data using CNN-XGBoost model: Experimental validation in a residential building. Sustainability 14(21), 14644 (2022).","journal-title":"Sustainability"},{"key":"59912_CR38","doi-asserted-by":"publisher","first-page":"3276","DOI":"10.3390\/s24113276","volume":"24","author":"I Khan","year":"2024","unstructured":"Khan, I., Zedadra, O., Guerrieri, A. & Spezzano, G. Occupancy prediction in IoT-enabled smart buildings: Technologies, methods, and future directions. Sensors 24, 3276. https:\/\/doi.org\/10.3390\/s24113276 (2024).","journal-title":"Sensors"},{"key":"59912_CR39","doi-asserted-by":"publisher","first-page":"109313","DOI":"10.1016\/j.buildenv.2022.109313","volume":"223","author":"M Parzinger","year":"2022","unstructured":"Parzinger, M. et al. Comparison of different training data sets from simulation and experimental measurement with artificial users for occupancy detection using machine learning methods random forest and LASSO. Build. Environ. 223, 109313. https:\/\/doi.org\/10.1016\/j.buildenv.2022.109313 (2022).","journal-title":"Build. Environ."},{"key":"59912_CR40","doi-asserted-by":"publisher","first-page":"114519","DOI":"10.1016\/j.enbuild.2024.114519","volume":"319","author":"K Bouyakhsaine","year":"2024","unstructured":"Bouyakhsaine, K., Brakez, A. & Draou, M. Prediction of residential building occupancy using machine learning with integrated sensor and survey data: Insights from a living lab in Morocco. Energy Build. 319, 114519 (2024).","journal-title":"Energy Build."},{"key":"59912_CR41","doi-asserted-by":"publisher","first-page":"109689","DOI":"10.1016\/j.buildenv.2022.109689","volume":"226","author":"ZD Tekler","year":"2022","unstructured":"Tekler, Z. D. & Chong, A. Occupancy prediction using deep learning approaches across multiple space types: A minimum sensing strategy. Build. Environ. 226, 109689. https:\/\/doi.org\/10.1016\/j.buildenv.2022.109689 (2022).","journal-title":"Build. Environ."},{"key":"59912_CR42","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.enbenv.2023.09.003","volume":"6","author":"S Chitnis","year":"2025","unstructured":"Chitnis, S., Somu, N. & Kowli, A. Occupancy estimation with environmental sensors: The possibilities and limitations, Energy. Built Environ. 6, 96\u2013108. https:\/\/doi.org\/10.1016\/j.enbenv.2023.09.003 (2025).","journal-title":"Built Environ."},{"key":"59912_CR43","doi-asserted-by":"publisher","first-page":"111382","DOI":"10.1016\/j.buildenv.2024.111382","volume":"254","author":"F Banihashemi","year":"2024","unstructured":"Banihashemi, F., Weber, M., Deghim, F., Zong, C. & Lang, W. Occupancy modeling on non-intrusive indoor environmental data through machine learning. Build. Environ. 254, 111382. https:\/\/doi.org\/10.1016\/j.buildenv.2024.111382 (2024).","journal-title":"Build. Environ."},{"issue":"3","key":"59912_CR44","doi-asserted-by":"publisher","first-page":"100018","DOI":"10.1016\/j.indenv.2024.100018","volume":"1","author":"Q Huang","year":"2024","unstructured":"Huang, Q., Syndicus, M., Frisch, J. & van Treeck, C. Spatial features of CO2 for occupancy detection in a naturally ventilated school building. Indoor Environments 1(3), 100018. https:\/\/doi.org\/10.1016\/j.indenv.2024.100018 (2024).","journal-title":"Indoor Environments"},{"key":"59912_CR45","doi-asserted-by":"publisher","first-page":"111319","DOI":"10.1016\/j.buildenv.2024.111319","volume":"254","author":"KH Andersen","year":"2024","unstructured":"Andersen, K. H. et al. Exploring occupant detection model generalizability for residential buildings using supervised learning with IEQ sensors. Build. Environ. 254, 111319. https:\/\/doi.org\/10.1016\/j.buildenv.2024.111319 (2024).","journal-title":"Build. Environ."},{"issue":"23","key":"59912_CR46","doi-asserted-by":"publisher","first-page":"9596","DOI":"10.3390\/s23239596","volume":"23","author":"A Tsanousa","year":"2023","unstructured":"Tsanousa, A., Moschou, C., Bektsis, E., Vrochidis, S. & Kompatsiaris, I. Fusion of environmental sensors for occupancy detection in a real construction site. Sensors. 23(23), 9596. https:\/\/doi.org\/10.3390\/s23239596 (2023).","journal-title":"Sensors"},{"issue":"2","key":"59912_CR47","doi-asserted-by":"publisher","first-page":"585","DOI":"10.3390\/s23020585","volume":"23","author":"J Kim","year":"2023","unstructured":"Kim, J., Bang, J., Choi, A., Moon, H. J. & Sung, M. Estimation of occupancy using IoT sensors and a carbon dioxide-based machine learning model with ventilation system and differential pressure data. Sensors 23(2), 585. https:\/\/doi.org\/10.3390\/s23020585 (2023).","journal-title":"Sensors"},{"issue":"3","key":"59912_CR48","doi-asserted-by":"publisher","first-page":"545","DOI":"10.3390\/buildings16030545","volume":"16","author":"M Skromule","year":"2026","unstructured":"Skromule, M., Kozlovskis, R., Tiscenko, D. & Judvaitis, J. Investigation of audio feature application for CO2 sensor-based occupancy detection enhancement. Buildings 16(3), 545. https:\/\/doi.org\/10.3390\/buildings16030545 (2026).","journal-title":"Buildings"},{"key":"59912_CR49","first-page":"4765","volume":"30","author":"SM Lundberg","year":"2017","unstructured":"Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30, 4765\u20134774 (2017).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"59912_CR50","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2024.115086","author":"R Minassian","year":"2025","unstructured":"Minassian, R., Mihi, A. S. & Shirazi, A. Optimizing indoor environmental prediction in smart buildings: a comparative analysis of deep learning models. Energy Build. https:\/\/doi.org\/10.1016\/j.enbuild.2024.115086 (2025).","journal-title":"Energy Build."},{"key":"59912_CR51","doi-asserted-by":"publisher","first-page":"114153","DOI":"10.1016\/j.enbuild.2024.114153","volume":"312","author":"S Zhang","year":"2024","unstructured":"Zhang, S. et al. Prediction of occupant thermal state via infrared thermography and explainable AI. Energy Build. 312, 114153. https:\/\/doi.org\/10.1016\/j.enbuild.2024.114153 (2024).","journal-title":"Energy Build."},{"key":"59912_CR52","doi-asserted-by":"publisher","first-page":"39466","DOI":"10.1038\/s41598-025-23134-4","volume":"15","author":"S Zhang","year":"2025","unstructured":"Zhang, S. & Kong, C. Deep learning and multi-objective optimization for real-time occupancy-based energy control in smart buildings. Sci. Rep. 15, 39466. https:\/\/doi.org\/10.1038\/s41598-025-23134-4 (2025).","journal-title":"Sci. Rep."},{"key":"59912_CR53","doi-asserted-by":"publisher","first-page":"105254","DOI":"10.1016\/j.engappai.2022.105254","volume":"115","author":"AN Sayed","year":"2022","unstructured":"Sayed, A. N., Himeur, Y. & Bensaali, F. Deep and transfer learning for building occupancy detection: A review and comparative analysis. Eng. Appl. Artif. Intell. 115, 105254 (2022).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"59912_CR54","doi-asserted-by":"publisher","first-page":"110807","DOI":"10.1016\/j.buildenv.2023.110807","volume":"244","author":"K Sun","year":"2023","unstructured":"Sun, K., Qaisar, I., Khan, M. A., Xing, T. & Zhao, Q. Building occupancy number prediction: A Transformer approach. Build. Environ. 244, 110807. https:\/\/doi.org\/10.1016\/j.buildenv.2023.110807 (2023).","journal-title":"Build. Environ."},{"key":"59912_CR55","doi-asserted-by":"publisher","first-page":"111355","DOI":"10.1016\/j.buildenv.2024.111355","volume":"253","author":"K Sun","year":"2024","unstructured":"Sun, K. DMFF: Deep multimodel feature fusion for building occupancy detection. Build. Environ. 253, 111355 (2024).","journal-title":"Build. Environ."},{"key":"59912_CR56","doi-asserted-by":"publisher","first-page":"9603","DOI":"10.3390\/s23239603","volume":"23","author":"MK Diarra","year":"2023","unstructured":"Diarra, M. K., Maniar, A., Masson, J. B., Marhic, B. & Delahoche, L. Occupancy state prediction by recurrent neural network (LSTM): Multi-room context. Sensors 23, 9603 (2023).","journal-title":"Sensors"},{"key":"59912_CR57","unstructured":"Ministry of Housing and Urban-Rural Development of the People\u2019s Republic of China. Standard for Testing Methods of Building Thermal Environment (JGJ\/T 347-2014); China Architecture & Building Press: Beijing, 2014. (in Chinese)"},{"issue":"10","key":"59912_CR58","doi-asserted-by":"publisher","first-page":"e0258281","DOI":"10.1371\/journal.pone.0258281","volume":"16","author":"E Duffy","year":"2021","unstructured":"Duffy, E., Huttunen, K., Lahnavik, R., Smeaton, A. F. & Morrin, A. Visualising household air pollution: Colorimetric sensor arrays for monitoring volatile organic compounds indoors. PLoS ONE 16(10), e0258281. https:\/\/doi.org\/10.1371\/journal.pone.0258281 (2021).","journal-title":"PLoS ONE"},{"issue":"2","key":"59912_CR59","first-page":"105","volume":"11","author":"A Gholamy","year":"2018","unstructured":"Gholamy, A., Kreinovich, V. & Kosheleva, O. Why 70\/30 or 80\/20 relation between training and testing sets: A pedagogical explanation. Int. J. Intell. Technol. Appl. Stat. 11, 105\u2013111 (2018).","journal-title":"Int. J. Intell. Technol. Appl. Stat."},{"key":"59912_CR60","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/s12273-017-0413-9","volume":"11","author":"H Rahman","year":"2018","unstructured":"Rahman, H. & Han, H. Bayesian estimation of occupancy distribution in a multi-room office building based on CO2 concentrations. Build. Simul. 11, 575\u2013583. https:\/\/doi.org\/10.1007\/s12273-017-0413-9 (2018).","journal-title":"Build. Simul."},{"key":"59912_CR61","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1007\/s10994-020-05910-7","volume":"109","author":"V Cerqueira","year":"2020","unstructured":"Cerqueira, V., Torgo, L. & Mozeti\u010d, I. Evaluating time series forecasting models: An empirical study on performance estimation methods. Mach. Learn. 109, 1997\u20132028 (2020).","journal-title":"Mach. Learn."},{"key":"59912_CR62","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1016\/j.ins.2011.12.028","volume":"191","author":"C Bergmeir","year":"2012","unstructured":"Bergmeir, C. & Ben\u00edtez, J. M. On the use of cross-validation for time series predictor evaluation. Inf. Sci. 191, 192\u2013213. https:\/\/doi.org\/10.1016\/j.ins.2011.12.028 (2012).","journal-title":"Inf. Sci."},{"issue":"10","key":"59912_CR63","doi-asserted-by":"publisher","first-page":"101046","DOI":"10.1016\/j.patter.2024.101046","volume":"5","author":"MA Lones","year":"2024","unstructured":"Lones, M. A. Avoiding common machine learning pitfalls. Patterns 5, 101046. https:\/\/doi.org\/10.1016\/j.patter.2024.101046 (2024).","journal-title":"Patterns"},{"key":"59912_CR64","doi-asserted-by":"publisher","first-page":"109811","DOI":"10.1016\/j.enbuild.2020.109811","volume":"212","author":"J Du","year":"2020","unstructured":"Du, J., Pan, W. & Yu, C. In-situ monitoring of occupant behavior in residential buildings\u00a0\u2012 A timely review. Energy Build. 212, 109811. https:\/\/doi.org\/10.1016\/j.enbuild.2020.109811 (2020).","journal-title":"Energy Build."},{"key":"59912_CR65","doi-asserted-by":"publisher","first-page":"106738","DOI":"10.1016\/j.buildenv.2020.106738","volume":"178","author":"W O\u2019Brien","year":"2020","unstructured":"O\u2019Brien, W. et al. Introducing IEA EBC annex 79: Key challenges and opportunities in the field of occupant-centric building design and operation. Build. Environ. 178, 106738. https:\/\/doi.org\/10.1016\/j.buildenv.2020.106738 (2020).","journal-title":"Build. Environ."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-59912-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-59912-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-59912-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T11:04:42Z","timestamp":1791975882000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-59912-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":65,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["59912"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-59912-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]},"assertion":[{"value":"25 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was reviewed and approved by the Institutional Review Board of Hangzhou Integrative Medicine Hospital (protocol code XZX2021101701) and Medical Academic Ethics Committee of Zhejiang University School of Medicine (protocol code 2020\u2013004). All methods were carried out in accordance with the Declaration of Helsinki. Informed consent was obtained from all subjects and their legal guardians prior to data collection.","order":2,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"32138"}}