{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T03:37:34Z","timestamp":1778211454365,"version":"3.51.4"},"reference-count":20,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T00:00:00Z","timestamp":1677024000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004489","name":"Mitacs Accelerate Program","doi-asserted-by":"publisher","award":["IT26852"],"award-info":[{"award-number":["IT26852"]}],"id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In-bed posture monitoring has become a prevalent area of research to help minimize the risk of pressure sore development and to increase sleep quality. This paper proposed 2D and 3D Convolutional Neural Networks, which are trained on images and videos of an open-access dataset consisting of 13 subjects\u2019 body heat maps captured from a pressure mat in 17 positions, respectively. The main goal of this paper is to detect the three main body positions: supine, left, and right. We compare the use of image and video data through 2D and 3D models in our classification. Since the dataset was imbalanced, three strategies were evaluated, i.e., down sampling, over sampling, and class weights. The best 3D model achieved accuracies of 98.90 \u00b1 1.05% and 97.80 \u00b1 2.14% for 5-fold and leave-one-subject-out (LOSO) cross validations, respectively. To compare the 3D model with 2D, four pre-trained 2D models were evaluated, where the best-performing model was the ResNet-18 with accuracies of 99.97 \u00b1 0.03% for 5-fold and 99.62 \u00b1 0.37% for LOSO. The proposed 2D and 3D models provided promising results for in-bed posture recognition and can be used in the future to further distinguish postures into more detailed subclasses. The outcome of this study can be used to remind caregivers at hospitals and long-term care facilitiesto reposition their patients if they do not reposition themselves naturally to prevent pressure ulcers. In addition, the evaluation of body postures and movements during sleep can help caregivers understand sleep quality.<\/jats:p>","DOI":"10.3390\/s23052430","type":"journal-article","created":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T02:01:25Z","timestamp":1677117685000},"page":"2430","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["In-Bed Posture Classification Using Deep Neural Network"],"prefix":"10.3390","volume":"23","author":[{"given":"Lindsay","family":"Stern","sequence":"first","affiliation":[{"name":"Institute of Biomedical Engineering, University of Toronto, Toronto, ON M5S 3G9, Canada"},{"name":"KITE Research Institute, Toronto Rehabilitation Institute, University Health Network, Toronto, ON M5G 2C4, Canada"}]},{"given":"Atena","family":"Roshan Fekr","sequence":"additional","affiliation":[{"name":"Institute of Biomedical Engineering, University of Toronto, Toronto, ON M5S 3G9, Canada"},{"name":"KITE Research Institute, Toronto Rehabilitation Institute, University Health Network, Toronto, ON M5G 2C4, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,22]]},"reference":[{"key":"ref_1","unstructured":"Kirman, C.N. (2020, March 26). What is the Mortality Rate for Pressure Injuries (Pressure Ulcers)? Medscape. Available online: https:\/\/emedicine.medscape.com\/article\/190115-overview#:~:text=Pressure%20injuries%20are%20listed%20as,of%20all%20patients%20with%20paraplegia.&text=As%20many%20as%20one%20third,within%20the%20next%2012%20months."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1109\/JBHI.2019.2899070","article-title":"Artificial Neural Network for in-Bed Posture Classification Using Bed-Sheet Pressure Sensors","volume":"24","author":"Matar","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1093\/sleep\/6.1.52","article-title":"Sleep Positions in the Young Adult and Their Relationship with the Subjective Quality of Sleep","volume":"6","author":"Gagnon","year":"1983","journal-title":"Sleep"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1018","DOI":"10.1378\/chest.118.4.1018","article-title":"Association of Body Position With Severity of Apneic Events in Patients With Severe Nonpositional Obstructive Sleep Apnea","volume":"118","author":"Oksenberg","year":"2000","journal-title":"Chest"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/S0378-3782(02)00025-7","article-title":"Effects of body position on sleep and arousal characteristics in infants","volume":"69","author":"Horne","year":"2002","journal-title":"Early Hum. Dev."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1109\/TBCAS.2021.3053602","article-title":"Deep Residual Networks for Sleep Posture Recognition with Unobtrusive Miniature Scale Smart Mat System","volume":"15","author":"Diao","year":"2021","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"055014","DOI":"10.1088\/2057-1976\/ab3ac9","article-title":"Pneumatic sensor for cardiorespiratory monitoring during sleep","volume":"5","author":"Yang","year":"2019","journal-title":"Biomed. Phys. Eng. Express"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Poyuan, M., Birjandtalab, J., Heydrazadeh, M., Nourani, M., and Ostadabbas, S. (2017, January 16\u201319). A Pressure Map Dataset for Posture and Subject Analytics. Proceedings of the IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Orlando, FL, USA.","DOI":"10.1109\/BHI.2017.7897206"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ostadabbas, S., Pouyan, M.B., Nourani, M., and Kehtarnavaz, N. (2014, January 22\u201324). In-Bed Posture Classification and Limb Identification. Proceedings of the IEEE Biomedical Circuits and Systems Conference (BioCAS), Lausanne, Switzerland.","DOI":"10.1109\/BioCAS.2014.6981663"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Metis, V., Galatas, G., Papangelis, A., Kosmopoulos, D., and Makedon, F. (2011, January 25\u201327). Recognition of Sleep Patterns Using a Bed Pressure Mat. Proceedings of the 4th International Conference on Pervasice Technologies Related to Assistive Environments, Crete, Greece.","DOI":"10.1145\/2141622.2141633"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wu, K., He, S., Fernie, G., and Fekr, A.R. (2020). Deep Neural Network for Slip Detection on Ice Surface. Sensors, 20.","DOI":"10.3390\/s20236883"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Janidarmian, M., Fekr, A.R., Radecka, K., and Zilic, Z. (2017). A Comprehensive Analysis on Wearable Acceleration Sensors in Human Activity Recognition. Sensors, 17.","DOI":"10.3390\/s17030529"},{"key":"ref_13","unstructured":"PhysioNet (2017, September 28). A Pressure Map Dataset for In-bed Posture Classification. Available online: https:\/\/physionet.org\/content\/pmd\/1.0.0\/."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Carreira, J., and Zisserman, A. (2017, January 21\u201326). Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref_15","unstructured":"MathWorks (2022, August 08). Alexnet. Available online: https:\/\/www.mathworks.com\/help\/deeplearning\/ref\/alexnet.html."},{"key":"ref_16","unstructured":"MathWorks (2022, August 08). Resnet18. Available online: https:\/\/www.mathworks.com\/help\/deeplearning\/ref\/resnet18.html."},{"key":"ref_17","unstructured":"MathWorks (2022, August 08). Googlenet. Available online: https:\/\/www.mathworks.com\/help\/deeplearning\/ref\/googlenet.html."},{"key":"ref_18","unstructured":"MathWorks (2022, August 08). Shufflenet. Available online: https:\/\/www.mathworks.com\/help\/deeplearning\/ref\/shufflenet.html."},{"key":"ref_19","unstructured":"MathWorks (2022, August 08). Transfer Learning for Training Deep Learning Mode. Available online: https:\/\/www.mathworks.com\/discovery\/transfer-learning.html."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Matar, G., Lina, J.-M., Carrier, J., Riley, A., and Kaddoum, G. (2016, January 14\u201316). Internet of Things in sleep monitoring: An application for posture recognition using supervised learning. Proceedings of the IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom), Munich, Germany.","DOI":"10.1109\/HealthCom.2016.7749469"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/5\/2430\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:39:23Z","timestamp":1760121563000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/5\/2430"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,22]]},"references-count":20,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["s23052430"],"URL":"https:\/\/doi.org\/10.3390\/s23052430","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,22]]}}}