{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:46:53Z","timestamp":1778010413477,"version":"3.51.4"},"reference-count":45,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T00:00:00Z","timestamp":1674172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research (CIHR)","doi-asserted-by":"publisher","award":["FDN-148450"],"award-info":[{"award-number":["FDN-148450"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Tele-rehabilitation has the potential to considerably change the way patients are monitored from their homes during the care process, by providing equitable access without the need to travel to rehab centers or shoulder the high cost of personal in-home services. Developing a tele-rehab platform with the capability of automating exercise guidance is likely to have a significant impact on rehabilitation outcomes. In this paper, a new vision-based biofeedback system is designed and validated to identify the quality of performed exercises. This new system will help patients to refine their movements to get the most out of their plan of care. An open dataset was used, which consisted of data from 30 participants performing nine different exercises. Each exercise was labeled as \u201cCorrectly\u201d or \u201cIncorrectly\u201d executed by five clinicians. We used a pre-trained 3D Convolution Neural Network (3D-CNN) to design our biofeedback system. The proposed system achieved average accuracy values of 90.57% \u00b1 9.17% and 83.78% \u00b1 7.63% using 10-Fold and Leave-One-Subject-Out (LOSO) cross validation, respectively. In addition, we obtained average F1-scores of 71.78% \u00b1 5.68% using 10-Fold and 60.64% \u00b1 21.3% using LOSO validation. The proposed 3D-CNN was able to classify the rehabilitation videos and feedback on the quality of exercises to help users modify their movement patterns.<\/jats:p>","DOI":"10.3390\/s23031206","type":"journal-article","created":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T06:52:41Z","timestamp":1674197561000},"page":"1206","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Design and Validation of Vision-Based Exercise Biofeedback for Tele-Rehabilitation"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6709-8618","authenticated-orcid":false,"given":"Ali","family":"Barzegar Khanghah","sequence":"first","affiliation":[{"name":"KITE Research Institute, Toronto Rehabilitation Institute, University Health Network, 550 University Ave, Toronto, ON M5G 2A2, Canada"},{"name":"Institute of Biomedical Engineering, University of Toronto, 164 College St., Toronto, ON M5S 3G9, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4821-7650","authenticated-orcid":false,"given":"Geoff","family":"Fernie","sequence":"additional","affiliation":[{"name":"KITE Research Institute, Toronto Rehabilitation Institute, University Health Network, 550 University Ave, Toronto, ON M5G 2A2, Canada"},{"name":"Institute of Biomedical Engineering, University of Toronto, 164 College St., Toronto, ON M5S 3G9, Canada"},{"name":"Department of Surgery, University of Toronto, 149 College Street, Toronto, ON M5T 1P5, Canada"}]},{"given":"Atena","family":"Roshan Fekr","sequence":"additional","affiliation":[{"name":"KITE Research Institute, Toronto Rehabilitation Institute, University Health Network, 550 University Ave, Toronto, ON M5G 2A2, Canada"},{"name":"Institute of Biomedical Engineering, University of Toronto, 164 College St., Toronto, ON M5S 3G9, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"929","DOI":"10.5465\/amj.2014.4004","article-title":"Aging populations and management","volume":"57","author":"Kulik","year":"2014","journal-title":"Acad. Manag. J."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"252","DOI":"10.2522\/ptj.20150079","article-title":"Telehealth implementation in a skilled nursing facility: Case report for physical therapist practice in Washington","volume":"96","author":"Lee","year":"2016","journal-title":"Phys. Ther."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"65","DOI":"10.5195\/ijt.2018.6258","article-title":"The effect of telerehabilitation on missed appointment rates","volume":"10","author":"Covert","year":"2018","journal-title":"Int. J. Telerehabilitation"},{"key":"ref_4","unstructured":"Ontario Physiotherapy Association (2021, August 03). Telerehabilitation In Physiotherapy During the Covid-19 Pandemic, Survey Report. Available online: https:\/\/www.google.com\/search?q=\u201ctelerehabilitation+in+physiotherapy+during+the+covid-19+pandemic\u201d%2c+survey+report%2c+ontario+physiotherapy+association%2c+august+2020&rlz=1c1sqjl_enir917ir917&oq=\u201ctelerehabilitation+in+physiotherapy+during+the+covid-19+pandemic\u201d%2c+survey+report%2c+ontario+physiotherapy+association%2c+august+2020&aqs=chrome..69i57.559j0j4&sourceid=chrome&ie=utf-8."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1177\/1357633X16634518","article-title":"Clinical outcomes of remote asynchronous telerehabilitation are equivalent to traditional therapy following total knee arthroplasty: A randomized control study","volume":"23","author":"Bini","year":"2017","journal-title":"J. Telemed. Telecare"},{"key":"ref_6","unstructured":"World Health Organization (2022, October 05). Global Estimates of The Need for Rehabilitation. Available online: https:\/\/www.who.int\/teams\/noncommunicable-diseases\/sensory-functions-disability-and-rehabilitation\/global-estimates-of-the-need-for-rehabilitation."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e7511","DOI":"10.2196\/rehab.7511","article-title":"Telerehabilitation: Review of the State-of-the-Art and Areas of Application","volume":"4","author":"Peretti","year":"2017","journal-title":"JMIR Rehabil. Assist. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e059985","DOI":"10.1136\/bmjopen-2021-059985","article-title":"Scoping review of remote rehabilitation (telerehabilitation) services to support people with vision impairment","volume":"12","author":"Jones","year":"2022","journal-title":"BMJ Open"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Shem, K., Irgens, I., and Alexander, M. (2022). Telerehabilitation, Elsevier.","DOI":"10.1016\/B978-0-323-82486-6.00012-5"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Condino, S., Turini, G., Viglialoro, R., Gesi, M., and Ferrari, V. (2019). Wearable Augmented Reality Application for Shoulder Rehabilitation. Electronics, 8.","DOI":"10.3390\/electronics8101178"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Naeemabadi, M.R., Dinesen, B.I., Andersen, O.K., Najafi, S., and Hansen, J. (2018, January 19\u201321). Evaluating accuracy and usability of Microsoft Kinect sensors and wearable sensor for tele knee rehabilitation after knee operation. Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies, Biostec 2018, Madeira, Portugal.","DOI":"10.5220\/0006578201280135"},{"key":"ref_12","first-page":"205566831986854","article-title":"Evaluating the use of machine learning in the assessment of joint angle using a single inertial sensor","volume":"6","author":"Argent","year":"2019","journal-title":"J. Rehabil. Assist. Technol. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kim, J.Y., Park, G., Lee, S.A., and Nam, Y. (2020). Analysis of Machine Learning-Based Assessment for Elbow Spasticity Using Inertial Sensors. Sensors, 20.","DOI":"10.3390\/s20061622"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"075007","DOI":"10.1088\/1361-6579\/aacfd9","article-title":"Shoulder physiotherapy exercise recognition: Machine learning the inertial signals from a smartwatch","volume":"39","author":"Burns","year":"2018","journal-title":"Physiol. Meas."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Fekr, A.R., Janidarmian, M., Radecka, K., and Zilic, Z. (2014, January 1\u20134). Multi-sensor blind recalibration in mHealth applications. Proceedings of the 2014 IEEE Canada International Humanitarian Technology Conference\u2013(IHTC), Montreal, QC, Canada.","DOI":"10.1109\/IHTC.2014.7147538"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MAES.2014.130191","article-title":"Navigation using inertial sensors","volume":"30","author":"Groves","year":"2015","journal-title":"IEEE Aerosp. Electron. Syst. Mag."},{"key":"ref_17","unstructured":"Ma, J. (2019). Innovative Intelligent Sensors to Objectively Understand Exercise Interventions for Older Adults. [Ph.D. Thesis, Loughborough University]. Available online: https:\/\/www.google.com\/search?q=%5B14%5D+Jianjia+Ma%2C+Ph.D.+Thesis%2C+\u201cInnovative+Intelligent+Sensors+to+Objectively+Understand+Exercise+Interventions+for+Older+Adults\u201d%2C+May+2019.&rlz=1C1SQJL_enIR917IR917&oq=%5B14%5D%09Jianjia+Ma%2C+Ph.D.+Thesis%2C+\u201cInnovative+Intelligent+Sensors+to+Objectively+Understand+Exercise+Interventions+for+Older+Adults\u201d%2C+May+2019.&aqs=chrome..69i57.573j0j9&sourceid=chrome&ie=UTF-8."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"104077","DOI":"10.1016\/j.jbi.2022.104077","article-title":"Automatic Evaluation of Motor Rehabilitation Exercises Based on Deep Mixture Density Neural Networks","volume":"130","author":"Mottaghi","year":"2022","journal-title":"J. Biomed. Inform."},{"key":"ref_19","unstructured":"Houglum, P., and Bertoti, D. (2011). Brunnstrom\u2019s Clinical Kinesiology, FA Davis."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"117165","DOI":"10.1016\/j.eswa.2022.117165","article-title":"Machine Learning role in clinical decision-making: Neuro-rehabilitation video game","volume":"201","author":"Esfahlani","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1824","DOI":"10.1109\/TNSRE.2019.2934097","article-title":"Towards on-demand virtual physical therapist: Machine learning-based patient action understanding, assessment and task recommendation","volume":"27","author":"Wei","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Pham, Q.T., Nguyen, V.A., Nguyen, T.T., Nguyen, D.A., Nguyen, D.G., Pham, D.T., and Le, T.L. (2022, January 27\u201329). Automatic recognition and assessment of physical exercises from RGB images. Proceedings of the 2022 IEEE Ninth International Conference on Communications and Electronics (ICCE), Nha Trang, Vietnam.","DOI":"10.1109\/ICCE55644.2022.9852094"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"105638","DOI":"10.1109\/ACCESS.2019.2932101","article-title":"Physiological Function Assessment Based on Kinect V2","volume":"7","author":"Cao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yang, F., Wu, Y., Sakti, S., and Nakamura, S. (2020, January 10). Make Skeleton-based Action Recognition Model Smaller, Faster and Better. Proceedings of the ACM Multimedia Asia, New York, NY, USA.","DOI":"10.1145\/3338533.3366569"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yan, H., Hu, B., Chen, G., and Zhengyuan, E. (2020, January 24\u201326). Real-Time Continuous Human Rehabilitation Action Recognition using OpenPose and FCN. Proceedings of the 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), Shenzhen, China.","DOI":"10.1109\/AEMCSE50948.2020.00058"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Barriga, A., Conejero, J.M., Hern\u00e1ndez, J., Jurado, E., Moguel, E., and S\u00e1nchez-Figueroa, F. (2016). A Vision-Based Approach for Building Telecare and Telerehabilitation Services. Sensors, 16.","DOI":"10.3390\/s16101724"},{"key":"ref_27","first-page":"1563707","article-title":"Automated Detection of Rehabilitation Exercise by Stroke Patients Using 3-Layer CNN-LSTM Model","volume":"2022","author":"Rahman","year":"2020","journal-title":"J. Healthc. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Yahya, M., Shah, J., Kadir, K., Warsi, A., Khan, S., and Nasir, H. (2019, January 20\u201323). Accurate shoulder joint angle estimation using single RGB camera for rehabilitation. Proceedings of the 2019 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Auckland, New Zealand.","DOI":"10.1109\/I2MTC.2019.8827104"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3001","DOI":"10.1109\/TCSVT.2018.2875441","article-title":"Multi-Stream Deep Neural Networks for RGB-D Egocentric Action Recognition","volume":"29","author":"Tang","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"145227","DOI":"10.1109\/ACCESS.2019.2944652","article-title":"A Novel Combination Model of Convolutional Neural Network and Long Short-Term Memory Network for Upper Limb Evaluation Using Kinect-Based System","volume":"7","author":"Cao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Miron, A., Sadawi, N., Ismail, W., Hussain, H., and Grosan, C. (2021). Intellirehabds (Irds)\u2014A dataset of physical rehabilitation movements. Data, 6.","DOI":"10.3390\/data6050046"},{"key":"ref_32","unstructured":"(2022, April 28). \u201cIntelliRehabDS\u2013A Dataset of Physical Rehabilitation Movements | Zenodo.\u201d. Available online: https:\/\/zenodo.org\/record\/4610859."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"23649","DOI":"10.1007\/s11042-020-10249-1","article-title":"Protection of visual privacy in videos acquired with RGB cameras for active and assisted living applications","volume":"80","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"ref_34","unstructured":"Zhang, C., Tian, Y., and Capezuti, E. (2012). Computers Helping People with Special Needs, Springer."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Stone, E.E., and Skubic, M. (2011, January 23\u201326). Evaluation of an inexpensive depth camera for passive in-home fall risk assessment. Proceedings of the 2011 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops, Dublin, Ireland.","DOI":"10.4108\/icst.pervasivehealth.2011.246034"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Momin, M.S., Sufian, A., Barman, D., Dutta, P., Dong, M., and Leo, M. (2022). In-Home Older Adults\u2019 Activity Pattern Monitoring Using Depth Sensors: A Review. Sensors, 22.","DOI":"10.3390\/s22239067"},{"key":"ref_37","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 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref_38","unstructured":"Soomro, K., Zamir, A.R., and Shah, M. (2022, April 28). UCF101: A Dataset of 101 Human Actions Classes from Videos in The Wild. Available online: https:\/\/arxiv.org\/abs\/1212.0402."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., and Serre, T. (2011, January 6\u201313). HMDB: A large video database for human motion recognition. Proceedings of the 2011 IEEE International Conference on Computer Vision, Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wang, H., and Schmid, C. (2013, January 1\u20138). Action recognition with improved trajectories. Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, NSW, Australia.","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref_41","unstructured":"Kingma, D.P., and Ba, J. (2015). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_42","first-page":"181","article-title":"Efficient AUC learning curve calculation","volume":"4304","author":"Bouckaert","year":"2006","journal-title":"Lect. Notes Comput. Sci. Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinforma"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Rybarczyk, Y., P\u00e9rez Medina, J.L., Leconte, L., Jimenes, K., Gonz\u00e1lez, M., and Esparza, D. (2019). Implementation and Assessment of an Intelligent Motor Tele-Rehabilitation Platform. Electronics, 8.","DOI":"10.3390\/electronics8010058"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"116990","DOI":"10.1016\/j.eswa.2022.116990","article-title":"Simultaneous exercise recognition and evaluation in prescribed routines: Approach to virtual coaches","volume":"199","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Goswami, A., and Vadakkepat, P. (2019). Humanoid Robotics: A Reference, Springer.","DOI":"10.1007\/978-94-007-6046-2"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/3\/1206\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:12:03Z","timestamp":1760119923000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/3\/1206"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,20]]},"references-count":45,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["s23031206"],"URL":"https:\/\/doi.org\/10.3390\/s23031206","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,20]]}}}