{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:15:53Z","timestamp":1789575353806,"version":"build-2803163510"},"reference-count":36,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of University and Research in the framework of PNC \u201cDARE\u2014Digital lifelong prevention project\u201d","award":["PNC0000002\u2014CUP B53C22006450001"],"award-info":[{"award-number":["PNC0000002\u2014CUP B53C22006450001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Sleep position recognition plays a crucial role in diagnosing and managing various health conditions, such as sleep apnea, pressure ulcers, and musculoskeletal disorders. Accurate monitoring of body posture during sleep can provide valuable insights for clinicians and support the development of intelligent healthcare systems. This research presents a comparative analysis of sleep position recognition using two distinct approaches: image-based deep learning and accelerometer-based classification. There are five classes: prone, supine, right side, left side, and wake up. For the image-based method, the Visual Geometry Group 16 (VGG16) convolutional neural network was fine-tuned with data augmentation strategies including rotation, reflection, scaling, and translation to enhance model generalization. The image-based model achieved an overall accuracy of 93.49%, with perfect precision and recall for \u201cright side\u201d and \u201cwakeup\u201d positions, but slightly lower performance for \u201cleft side\u201d and \u201csupine\u201d classes. In contrast, the accelerometer-based method employed a feedforward neural network trained on features extracted from segmented accelerometer data, such as signal sum, standard deviation, maximum, and spike count. This method yielded superior performance, reaching an accuracy exceeding 99.8% across most sleep positions. The \u201cwake up\u201d position was particularly easy to detect due to the absence of body movements such as heartbeat or respiration when the person is no longer in bed. The results demonstrate that while image-based models are effective, accelerometer-based classification offers higher precision and robustness, particularly in real-time and privacy-sensitive scenarios. Further comparisons of the system characteristics, data size, and training time are also carried out to offer crucial insights for selecting the appropriate technology in clinical, in-home, or embedded healthcare monitoring applications.<\/jats:p>","DOI":"10.3390\/s25123816","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:08:39Z","timestamp":1750309719000},"page":"3816","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking Accelerometer and CNN-Based Vision Systems for Sleep Posture Classification in Healthcare Applications"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3622-4327","authenticated-orcid":false,"given":"Minh Long","family":"Hoang","sequence":"first","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0705-527X","authenticated-orcid":false,"given":"Guido","family":"Matrella","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dalila","family":"Giannetto","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Craparo","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8944-2152","authenticated-orcid":false,"given":"Paolo","family":"Ciampolini","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"207","DOI":"10.4103\/atm.atm_214_22","article-title":"Comparing the Characteristics of Positional and Nonpositional Sleep Apnea Patients Among the Jordanian Population","volume":"17","author":"Toubasi","year":"2022","journal-title":"Ann. Thorac. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"100029","DOI":"10.1016\/j.aggp.2024.100029","article-title":"Advances in Technology-Driven Strategies for Preventing and Managing Bedsores: A Comprehensive Review","volume":"1","author":"Ghosh","year":"2024","journal-title":"Arch. Gerontol. Geriatr. Plus"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Gnarra, O., Calvello, C., Schirinzi, T., Beozzo, F., De Masi, C., Spanetta, M., Fernandes, M., Grillo, P., Cerroni, R., and Pierantozzi, M. (2023). Exploring the Association Linking Head Position and Sleep Architecture to Motor Impairment in Parkinson\u2019s Disease: An Exploratory Study. J. Pers. Med., 13.","DOI":"10.3390\/jpm13111591"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zampogna, A., Manoni, A., Asci, F., Liguori, C., Irrera, F., and Suppa, A. (2020). Shedding Light on Nocturnal Movements in Parkinson\u2019s Disease: Evidence from Wearable Technologies. Sensors, 20.","DOI":"10.3390\/s20185171"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chi, P., Bai, Y., Du, W., Wei, X., Liu, B., Zhao, S., Jiang, H., Chi, A., and Shao, M. (2025). Altered Muscle\u2013Brain Connectivity During Left and Right Biceps Brachii Isometric Contraction Following Sleep Deprivation: Insights from PLV and PDC. Sensors, 25.","DOI":"10.3390\/s25072162"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Giovannini, S., Brau, F., Galluzzo, V., Santagada, D.A., Loreti, C., Biscotti, L., Laudisio, A., Zuccal\u00e0, G., and Bernabei, R. (2022). Falls among Older Adults: Screening, Identification, Rehabilitation, and Management. Appl. Sci., 12.","DOI":"10.3390\/app12157934"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"114186","DOI":"10.1016\/j.measurement.2024.114186","article-title":"A Comprehensive Review of Elderly Fall Detection Using Wireless Communication and Artificial Intelligence Techniques","volume":"226","author":"Gharghan","year":"2024","journal-title":"Measurement"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Peruzzi, G., Galli, A., Giorgi, G., and Pozzebon, A. (2025). Sleep Posture Detection via Embedded Machine Learning on a Reduced Set of Pressure Sensors. Sensors, 25.","DOI":"10.3390\/s25020458"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hu, D., Gao, W., Ang, K.K., Hu, M., Huang, R., Chuai, G., and Li, X. (2025). CHMMConvScaleNet: A Hybrid Convolutional Neural Network and Continuous Hidden Markov Model with Multi-Scale Features for Sleep Posture Detection. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-93541-0"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Abdulsadig, R.S., Singh, S., Patel, Z., and Rodriguez-Villegas, E. (2022, January 11\u201315). Sleep Posture Detection Using an Accelerometer Placed on the Neck. Proceedings of the 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Glasgow, UK.","DOI":"10.1109\/EMBC48229.2022.9871300"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Hoang, M.L. (2024). Artificial Intelligence Development in Sensors and Computer Vision for Health Care and Automation Application, Bentham Science Publishers.","DOI":"10.2174\/97898153130551240101"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., and Pietrosanto, A. (2020, January 7\u20139). An Effective Method on Vibration Immunity for Inclinometer based on MEMS Accelerometer. Proceedings of the 2020 International Semiconductor Conference (CAS), Sinaia, Romania.","DOI":"10.1109\/CAS50358.2020.9267997"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., Matrella, G., and Ciampolini, P. (2024). Comparison of Machine Learning Algorithms for Heartbeat Detection Based on Accelerometric Signals Produced by a Smart Bed. Sensors, 24.","DOI":"10.3390\/s24061900"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Djaroudib, K., Lorenz, P., Belkacem Bouzida, R., and Merzougui, H. (2024). Skin Cancer Diagnosis Using VGG16 and Transfer Learning: Analyzing the Effects of Data Quality over Quantity on Model Efficiency. Appl. Sci., 14.","DOI":"10.3390\/app14177447"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Younis, A., Qiang, L., Nyatega, C.O., Adamu, M.J., and Kawuwa, H.B. (2022). Brain Tumor Analysis Using Deep Learning and VGG-16 Ensembling Learning Approaches. Appl. Sci., 12.","DOI":"10.3390\/app12147282"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Srinivasan, S., Gunasekaran, S., Mathivanan, S.K., Jayagopal, P., Khan, M.A., Alasiry, A., Marzougui, M., and Masood, A. (2023). A Framework of Faster CRNN and VGG16-Enhanced Region Proposal Network for Detection and Grade Classification of Knee RA. Diagnostics, 13.","DOI":"10.3390\/diagnostics13081385"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"18112","DOI":"10.1109\/JSTARS.2024.3459928","article-title":"Research on Improved VGG-16 Model Based on Transfer Learning for Acoustic Image Recognition of Underwater Search and Rescue Targets","volume":"17","author":"Liu","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Basamsetty, P., Kagitha, S., Nulu, P., and Pinniboyina, V. (2024, January 21\u201322). Medicine Recognition from Coversheet Using VGG16 Model. Proceedings of the 2024 IEEE North Karnataka Subsection Flagship International Conference (NKCon), Bagalkote, India.","DOI":"10.1109\/NKCon62728.2024.10774855"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Alshammari, A. (2022). Construction of VGG16 Convolution Neural Network (VGG16_CNN) Classifier with NestNet-Based Segmentation Paradigm for Brain Metastasis Classification. Sensors, 22.","DOI":"10.3390\/s22208076"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Stienecker, M., and Hagemeier, A. (2023). Developing Feedforward Neural Networks as Benchmark for Load Forecasting: Methodology Presentation and Application to Hospital Heat Load Forecasting. Energies, 16.","DOI":"10.3390\/en16042026"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sukharev, E., and Sukharev, M. (2023). Accelerometer Signal Classification Algorithms Based on Mel-Frequency Cepstrum and Fully Connected Neural Network. Networked Control Systems for Connected and Automated Vehicles (NN 2022), Springer.","DOI":"10.1007\/978-3-031-11058-0_35"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"He, Z., Sun, Y., and Zhang, Z. (2024). Human Activity Recognition Based on Deep Learning Regardless of Sensor Orientation. Appl. Sci., 14.","DOI":"10.3390\/app14093637"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Fridriksdottir, E., and Bonomi, A.G. (2020). Accelerometer-Based Human Activity Recognition for Patient Monitoring Using a Deep Neural Network. Sensors, 20.","DOI":"10.3390\/s20226424"},{"key":"ref_24","first-page":"5903","article-title":"XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging","volume":"44","author":"Phan","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1305","DOI":"10.1109\/JBHI.2020.3025900","article-title":"SleepPoseNet: Multi-View Learning for Sleep Postural Transition Recognition Using UWB","volume":"25","author":"Piriyajitakonkij","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"116309","DOI":"10.1016\/j.sna.2025.116309","article-title":"Metrological evaluation of contactless sleep position recognition using an accelerometric smart bed and machine learning","volume":"385","author":"Hoang","year":"2025","journal-title":"Sens. Actuators A Phys."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Elnaggar, O., Coenen, F., Hopkinson, A., Mason, L., and Paoletti, P. (2022). Sleep Posture One-Shot Learning Framework Using Kinematic Data Augmentation: In-Silico and In-Vivo Case Studies. arXiv.","DOI":"10.1016\/j.inffus.2023.02.003"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Li, C., Ren, G., and Wang, Z. (2025). Sleep Posture Recognition Method Based on Sparse Body Pressure Features. Appl. Sci., 15.","DOI":"10.3390\/app15094920"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hu, D., Gao, W., Ang, K.K., Hu, M., Chuai, G., and Huang, R. (2024). Smart Sleep Monitoring: Sparse Sensor-Based Spatiotemporal CNN for Sleep Posture Detection. Sensors, 24.","DOI":"10.3390\/s24154833"},{"key":"ref_30","unstructured":"Papillon, O., Goubran, R., Green, J., Larivi\u00e8re-Chartier, J., Higginson, C., Knoefel, F., and Robillard, R. (2025). Sleep Position Classification Using Transfer Learning for Bed-Based Pressure Sensors. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Al-Naji, A., Gibson, K., Lee, S.-H., and Chahl, J. (2017). Real Time Apnoea Monitoring of Children Using the Microsoft Kinect Sensor: A Pilot Study. Sensors, 17.","DOI":"10.3390\/s17020286"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Li, Y.-Y., Wang, S.-J., and Hung, Y.-P. (2022). A Vision-Based System for In-Sleep Upper-Body and Head Pose Classification. Sensors, 22.","DOI":"10.3390\/s22052014"},{"key":"ref_33","unstructured":"(2025, January 29). Analog Device ADXL355. Available online: https:\/\/www.analog.com\/en\/products\/adxl355.html."},{"key":"ref_34","unstructured":"(2025, January 19). STMicroelectronics B-L475E-IOT01A-STM32L4 Discovery Kit IoT Node, Low-Power Wireless, BLE, NFC, SubGHz, Wi-Fi. Available online: https:\/\/www.st.com\/en\/evaluation-tools\/b-l475e-iot01a.html."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Mienye, I.D., Swart, T.G., and Obaido, G. (2024). Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications. Information, 15.","DOI":"10.20944\/preprints202408.0748.v1"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Say\u0131lar, B.C., and Ceylan, O. (September, January 30). Grid Search Based Hyperparameter Optimization for Machine Learning Based Non-Intrusive Load Monitoring. Proceedings of the 2023 58th International Universities Power Engineering Conference (UPEC), Dublin, Ireland.","DOI":"10.1109\/UPEC57427.2023.10294565"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/12\/3816\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:54:30Z","timestamp":1760032470000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/12\/3816"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,18]]},"references-count":36,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["s25123816"],"URL":"https:\/\/doi.org\/10.3390\/s25123816","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,18]]}}}