{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T00:43:05Z","timestamp":1770424985754,"version":"3.49.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100008982","name":"Qatar National Research Fund","doi-asserted-by":"publisher","award":["NPRP14S-0401-210122"],"award-info":[{"award-number":["NPRP14S-0401-210122"]}],"id":[{"id":"10.13039\/100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004252","name":"Qatar University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004252","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Occupancy detection is crucial for various applications, including smart buildings, security systems, and energy management. This paper introduces a novel convolutional neural network (CNN) architecture based on an image encoding approach for accurate occupancy detection. Our network effectively extracts relevant features from occupancy images by leveraging deep learning and image processing techniques, enabling reliable and real-time detection. We employed an image encoding method that converts environmental time-series data into 2D image representations\u2014either grayscale or RGB-like\u2014depending on the input requirements of the CNN model. This transformation captures spatial and temporal characteristics of the data, allowing the network to learn more expressive occupancy-related patterns from raw 1D input. Additionally, we developed a custom CNN architecture optimized for the encoded images, enabling the network to identify key features and understand complex spatial relationships. We evaluated the performance of our CNN through extensive testing on well-known occupancy datasets. The results highlight the superiority of our approach, outperforming existing techniques in accuracy, precision, recall, and F1-score. Our model achieved impressive accuracies of 98.45%, 99.05%, and 97.32% across the three datasets used in this study.<\/jats:p>","DOI":"10.1007\/s00521-025-11348-6","type":"journal-article","created":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T10:43:00Z","timestamp":1748947380000},"page":"16487-16503","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and beyond"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6141-5785","authenticated-orcid":false,"given":"Aya Nabil","family":"Sayed","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sakib","family":"Mahmud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faycal","family":"Bensaali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad E. H.","family":"Chowdhury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yassine","family":"Himeur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,3]]},"reference":[{"key":"11348_CR1","doi-asserted-by":"publisher","first-page":"105254","DOI":"10.1016\/j.egyr.2021.11.216","volume":"115","author":"AN Sayed","year":"2022","unstructured":"Sayed AN, Himeur Y, Bensaali F (2022) Deep and transfer learning for building occupancy detection: A review and comparative analysis. Eng Appl Artif Intell 115:105254. https:\/\/doi.org\/10.1016\/j.egyr.2021.11.216","journal-title":"Eng Appl Artif Intell"},{"key":"11348_CR2","doi-asserted-by":"publisher","first-page":"112401","DOI":"10.1016\/j.rser.2022.112401","volume":"162","author":"M Elnour","year":"2022","unstructured":"Elnour M et al (2022) Performance and energy optimization of building automation and management systems: Towards smart sustainable carbon-neutral sports facilities. Renew Sustain Energy Rev 162:112401. https:\/\/doi.org\/10.1016\/j.rser.2022.112401","journal-title":"Renew Sustain Energy Rev"},{"key":"11348_CR3","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1177\/1420326X19875621","volume":"29","author":"D Trivedi","year":"2020","unstructured":"Trivedi D, Badarla V (2020) Occupancy detection systems for indoor environments: A survey of approaches and methods. Indoor Built Environ 29:1053\u20131069. https:\/\/doi.org\/10.1177\/1420326X19875621","journal-title":"Indoor Built Environ"},{"key":"11348_CR4","doi-asserted-by":"publisher","first-page":"106966","DOI":"10.1016\/j.buildenv.2020.106966","volume":"180","author":"L Rueda","year":"2020","unstructured":"Rueda L, Agbossou K, Cardenas A, Henao N, Kelouwani S (2020) A comprehensive review of approaches to building occupancy detection. Build Environ 180:106966. https:\/\/doi.org\/10.1016\/j.buildenv.2020.106966","journal-title":"Build Environ"},{"key":"11348_CR5","doi-asserted-by":"publisher","first-page":"110457","DOI":"10.1016\/j.buildenv.2023.110457","volume":"240","author":"B Kula","year":"2023","unstructured":"Kula B et al (2023) Laboratory testing methods to evaluate the reliability of occupancy sensors for commercial building applications. Build Environ 240:110457. https:\/\/doi.org\/10.1016\/j.buildenv.2023.110457","journal-title":"Build Environ"},{"key":"11348_CR6","doi-asserted-by":"publisher","first-page":"2388","DOI":"10.3390\/en16052388","volume":"16","author":"AN Sayed","year":"2023","unstructured":"Sayed AN, Bensaali F, Himeur Y, Houchati M (2023) Edge-based real-time occupancy detection system through a non-intrusive sensing system. Energies 16:2388. https:\/\/doi.org\/10.3390\/en16052388","journal-title":"Energies"},{"key":"11348_CR7","doi-asserted-by":"publisher","first-page":"121823","DOI":"10.1016\/j.apenergy.2023.121823","volume":"351","author":"K Li","year":"2023","unstructured":"Li K et al (2023) A novel short-term multi-energy load forecasting method for integrated energy system based on feature separation-fusion technology and improved cnn. Appl Energy 351:121823. https:\/\/doi.org\/10.1016\/j.apenergy.2023.121823","journal-title":"Appl Energy"},{"key":"11348_CR8","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1016\/j.apenergy.2019.02.056","volume":"240","author":"Y Wei","year":"2019","unstructured":"Wei Y et al (2019) Prediction of occupancy level and energy consumption in office building using blind system identification and neural networks. Appl Energy 240:276\u2013294. https:\/\/doi.org\/10.1016\/j.apenergy.2019.02.056","journal-title":"Appl Energy"},{"key":"11348_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2024.111382","author":"F Banihashemi","year":"2024","unstructured":"Banihashemi F, Weber M, Deghim F, Zong C, Lang W (2024) Occupancy modeling on non-intrusive indoor environmental data through machine learning. Build Environ. https:\/\/doi.org\/10.1016\/j.buildenv.2024.111382","journal-title":"Build Environ"},{"key":"11348_CR10","doi-asserted-by":"publisher","unstructured":"Mahmud S, Houchati M, Bensaali F, Chowdhury MEH (2024) Non-intrusive load state monitoring through smart meter disaggregation using 1d deep reconstruction networks https:\/\/doi.org\/10.2139\/ssrn.4795206","DOI":"10.2139\/ssrn.4795206"},{"key":"11348_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2025.112635","author":"S Mahmud","year":"2025","unstructured":"Mahmud S, Bensaali F, Chowdhury MEH, Houchati M (2025) Multimodal feature fusion and ensemble learning for non-intrusive occupancy monitoring using smart meters. Build Environ. https:\/\/doi.org\/10.1016\/j.buildenv.2025.112635","journal-title":"Build Environ"},{"key":"11348_CR12","doi-asserted-by":"publisher","unstructured":"Sayed AN, Hamila R, Himeur Y, Bensaali F (2022). Employing information theoretic metrics with data-driven occupancy detection approaches: A comparative analysis. https:\/\/doi.org\/10.1109\/ICSPIS57063.2022.10002508","DOI":"10.1109\/ICSPIS57063.2022.10002508"},{"key":"11348_CR13","doi-asserted-by":"publisher","first-page":"105786","DOI":"10.1016\/j.engappai.2022.105786","volume":"119","author":"AN Sayed","year":"2023","unstructured":"Sayed AN, Himeur Y, Bensaali F (2023) From time-series to 2d images for building occupancy prediction using deep transfer learning. Eng Appl Artif Intell 119:105786. https:\/\/doi.org\/10.1016\/j.engappai.2022.105786","journal-title":"Eng Appl Artif Intell"},{"key":"11348_CR14","doi-asserted-by":"publisher","first-page":"105775","DOI":"10.1016\/j.engappai.2022.105775","volume":"119","author":"A Copiaco","year":"2023","unstructured":"Copiaco A et al (2023) An innovative deep anomaly detection of building energy consumption using energy time-series images. Eng Appl Artif Intell 119:105775. https:\/\/doi.org\/10.1016\/j.engappai.2022.105775","journal-title":"Eng Appl Artif Intell"},{"key":"11348_CR15","doi-asserted-by":"crossref","unstructured":"Elmir Y, Himeur Y, Amira A (2023) Ecg classification using deep cnn and gramian angular field. arXiv preprint arXiv:2308.02395","DOI":"10.1109\/BigDataService58306.2023.00026"},{"key":"11348_CR16","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.3390\/s21041036","volume":"21","author":"S Arvidsson","year":"2021","unstructured":"Arvidsson S, Gullstrand M, Sirmacek B, Riveiro M (2021) Sensor fusion and convolutional neural networks for indoor occupancy prediction using multiple low-cost low-resolution heat sensor data. Sensors 21:1036. https:\/\/doi.org\/10.3390\/s21041036","journal-title":"Sensors"},{"key":"11348_CR17","doi-asserted-by":"publisher","first-page":"111593","DOI":"10.1016\/j.enbuild.2021.111593","volume":"254","author":"K Sun","year":"2022","unstructured":"Sun K, Zhao Q, Zhang Z, Hu X (2022) 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","journal-title":"Energy Build"},{"key":"11348_CR18","unstructured":"Vora A, Chilaka V (2018) Fchd: Fast and accurate head detection in crowded scenes. arXiv preprint arXiv:1809.08766"},{"key":"11348_CR19","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1109\/JIOT.2022.3201877","volume":"10","author":"S Hu","year":"2022","unstructured":"Hu S, Wang P, Hoare C, O\u2019Donnell J (2022) Building occupancy detection and localization using cctv camera and deep learning. IEEE Internet Things J 10:597\u2013608. https:\/\/doi.org\/10.1109\/JIOT.2022.3201877","journal-title":"IEEE Internet Things J"},{"key":"11348_CR20","doi-asserted-by":"publisher","first-page":"3692","DOI":"10.3390\/s22103692","volume":"22","author":"L Monti","year":"2022","unstructured":"Monti L et al (2022) Edge-based transfer learning for classroom occupancy detection in a smart campus context. Sensors 22:3692. https:\/\/doi.org\/10.3390\/s22103692","journal-title":"Sensors"},{"key":"11348_CR21","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"11348_CR22","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 (2022) Indoor occupancy detection based on environmental data using cnn-xgboost model: Experimental validation in a residential building. Sustainability 14:14644. https:\/\/doi.org\/10.3390\/su142114644","journal-title":"Sustainability"},{"key":"11348_CR23","unstructured":"Sayed AN, Bensaali F, Himeur Y, Houchati M, Ben\u00a0Ahmed M, Boudhir AA, El\u00a0Meouche R, Karas \u0130.R (2024) (eds) Image transformation approaches for occupancy detection: A comprehensive analysis. Ben\u00a0Ahmed, M., Boudhir, A.\u00a0A., El\u00a0Meouche, R. & Karas, \u0130.\u00a0R. (eds.) Innovations in Smart Cities Applications Volume 7, 303\u2013311 Springer Nature Switzerland, Cham"},{"key":"11348_CR24","doi-asserted-by":"publisher","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: Inverted residuals and linear bottlenecks https:\/\/doi.org\/10.1109\/CVPR.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"11348_CR25","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016). Deep residual learning for image recognition. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"11348_CR26","unstructured":"Gholamalinezhad H, Khosravi H (2020) Pooling methods in deep neural networks, a review. arXiv preprint arXiv:2009.07485"},{"key":"11348_CR27","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.patcog.2016.01.030","volume":"55","author":"Y Liu","year":"2016","unstructured":"Liu Y, Zhang Y-M, Zhang X-Y, Liu C-L (2016) Adaptive spatial pooling for image classification. Pattern Recogn 55:58\u201367. https:\/\/doi.org\/10.1016\/j.patcog.2016.01.030","journal-title":"Pattern Recogn"},{"key":"11348_CR28","unstructured":"torch.Tensor.view \u2014 PyTorch 2.6 documentation \u2014 pytorch.org. https:\/\/pytorch.org\/docs\/stable\/generated\/torch.Tensor.view.html. [Accessed 05-02-2025]"},{"key":"11348_CR29","unstructured":"Kyurkchiev N, Iliev A, Rahnev A (2019) Some families of sigmoid functions: Applications to growth theory. Lap Lambert Academic Publishing, Saarbrucken, Germany"},{"key":"11348_CR30","doi-asserted-by":"publisher","unstructured":"Santurkar S, Tsipras D, Ilyas A, Madry A (2018) How does batch normalization help optimization? Advances in neural information processing systems 31 https:\/\/doi.org\/10.48550\/arXiv.1805.11604","DOI":"10.48550\/arXiv.1805.11604"},{"key":"11348_CR31","unstructured":"Agarap AF (2018) Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375"},{"key":"11348_CR32","doi-asserted-by":"publisher","unstructured":"Willocx M (2019). Occupancy detection in a student room. https:\/\/doi.org\/10.7910\/DVN\/BIIFAJ","DOI":"10.7910\/DVN\/BIIFAJ"},{"key":"11348_CR33","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.enbuild.2015.11.071","volume":"112","author":"LM Candanedo","year":"2016","unstructured":"Candanedo LM, Feldheim V (2016) 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","journal-title":"Energy Build"},{"key":"11348_CR34","doi-asserted-by":"publisher","first-page":"6579","DOI":"10.3390\/s20226579","volume":"20","author":"A Vela","year":"2020","unstructured":"Vela A, Alvarado-Uribe J, Davila M, Hernandez-Gress N, Ceballos HG (2020) Estimating occupancy levels in enclosed spaces using environmental variables: A fitness gym and living room as evaluation scenarios. Sensors 20:6579. https:\/\/doi.org\/10.3390\/s20226579","journal-title":"Sensors"},{"key":"11348_CR35","unstructured":"Multiclass Receiver Operating Characteristic (ROC) \u2014 scikit-learn.org. https:\/\/scikit-learn.org\/stable\/auto_examples\/model_selection\/plot_roc.html. [Accessed 06-02-2025]"},{"key":"11348_CR36","doi-asserted-by":"publisher","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization 2921\u20132929. https:\/\/doi.org\/10.1109\/CVPR.2016.319","DOI":"10.1109\/CVPR.2016.319"},{"key":"11348_CR37","doi-asserted-by":"publisher","unstructured":"Wang H et al. (2020) Score-cam: Score-weighted visual explanations for convolutional neural networks, 111\u2013119 https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00020","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"11348_CR38","doi-asserted-by":"publisher","unstructured":"Selvaraju RR et al. (2017) Grad-cam: Visual explanations from deep networks via gradient-based localization, 618\u2013626 https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"11348_CR39","doi-asserted-by":"publisher","first-page":"2335","DOI":"10.1007\/s00530-022-00960-4","volume":"28","author":"Q Teng","year":"2022","unstructured":"Teng Q, Liu Z, Song Y, Han K, Lu Y (2022) A survey on the interpretability of deep learning in medical diagnosis. Multimed Syst 28:2335\u20132355. https:\/\/doi.org\/10.1007\/s00530-022-00960-4","journal-title":"Multimed Syst"},{"key":"11348_CR40","doi-asserted-by":"publisher","unstructured":"Saxen F et al. (2019) Face attribute detection with mobilenetv2 and nasnet-mobile https:\/\/doi.org\/10.1109\/ISPA.2019.8868585","DOI":"10.1109\/ISPA.2019.8868585"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11348-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11348-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11348-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T13:01:22Z","timestamp":1753102882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11348-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,3]]},"references-count":40,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["11348"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11348-6","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,3]]},"assertion":[{"value":"10 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}