{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T19:08:33Z","timestamp":1775329713197,"version":"3.50.1"},"reference-count":33,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Telephysiotherapy has emerged as a vital solution for delivering remote healthcare, particularly in response to global challenges such as the COVID-19 pandemic. This study seeks to enhance telephysiotherapy by developing a system capable of accurately classifying physiotherapeutic exercises using PoseNet, a state-of-the-art pose estimation model. A dataset was collected from 49 participants (35 males, 14 females) performing seven distinct exercises, with twelve anatomical landmarks then extracted using the Google MediaPipe library. Each landmark was represented by four features, which were used for classification. The core challenge addressed in this research involves ensuring accurate and real-time exercise classification across diverse body morphologies and exercise types. Several tree-based classifiers, including Random Forest, Extra Tree Classifier, XGBoost, LightGBM, and Hist Gradient Boosting, were employed. Furthermore, two novel ensemble models called RandomLightHist Fusion and StackedXLightRF are proposed to enhance classification accuracy. The RandomLightHist Fusion model achieved superior accuracy of 99.6%, demonstrating the system\u2019s robustness and effectiveness. This innovation offers a practical solution for providing real-time feedback in telephysiotherapy, with potential to improve patient outcomes through accurate monitoring and assessment of exercise performance.<\/jats:p>","DOI":"10.3390\/s24196325","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T07:19:37Z","timestamp":1727680777000},"page":"6325","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Smart Physiotherapy: Advancing Arm-Based Exercise Classification with PoseNet and Ensemble Models"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6989-4271","authenticated-orcid":false,"given":"Shahzad","family":"Hussain","sequence":"first","affiliation":[{"name":"Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0671-2060","authenticated-orcid":false,"given":"Hafeez","family":"Siddiqui","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2468-8471","authenticated-orcid":false,"given":"Adil","family":"Saleem","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8881-1307","authenticated-orcid":false,"given":"Muhammad","family":"Raza","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan"},{"name":"Faculty of Computing, Riphah International University, 2 KM McDonald\u2019s Lahore Multan Bypass Road, Sahiwal 5700, Punjab, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9872-3082","authenticated-orcid":false,"given":"Josep","family":"Alemany-Iturriaga","sequence":"additional","affiliation":[{"name":"Facultad de Ciencias Sociales y Humanidades, Universidad Europea del Atl\u00e1ntico, Isabel Torres 21, 39011 Santander, Spain"},{"name":"Departamento de Ciencias de Lenguaje, Educaci\u00f3n y Comunicaciones, Universidad Internacional Iberoamericana Arecibo, Arecibo, PR 00613, USA"},{"name":"Universidad de La Romana, Edificio G&G, C\/ H\u00e9ctor Ren\u00e9 Gil, Esquina C\/ Francisco Castillo Marquez, La Romana 22000, Dominican Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9795-0904","authenticated-orcid":false,"given":"\u00c1lvaro","family":"Velarde-Sotres","sequence":"additional","affiliation":[{"name":"Facultad de Ciencias de la Salud, Universidad Europea del Atl\u00e1ntico, 39011 Santander, Spain"},{"name":"Departamento de Salud, Universidad Internacional Iberoamericana, Campeche 24560, Mexico"},{"name":"Faculdade de Ci\u00eancias de Sa\u00fade, Universidade Internacional do Cuanza Bairro Kaluanda, Cuito EN 250, Bi\u00e9, Angola"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3134-7720","authenticated-orcid":false,"given":"Isabel","family":"D\u00edez","sequence":"additional","affiliation":[{"name":"Department of Signal Theory, Communications and Telematics Engineering, University of Valladolid, 47011 Valladolid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6431-5357","authenticated-orcid":false,"given":"Sandra","family":"Dudley","sequence":"additional","affiliation":[{"name":"Bioengineering Research Centre, School of Engineering, London South Bank University, 103 Borough Road, London SE1 0AA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"What is telehealth?","volume":"4","author":"Catalyst","year":"2018","journal-title":"NEJM Catal."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Chua, J., Ong, L.-Y., and Leow, M.-C. (2021). Telehealth using PoseNet-based system for in-home rehabilitation. Future Internet, 13.","DOI":"10.3390\/fi13070173"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1093\/jamia\/ocaa067","article-title":"Telehealth transformation: COVID-19 and the rise of virtual care","volume":"27","author":"Wosik","year":"2020","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1111\/imj.15222","article-title":"Effect of the COVID-19 induced phase of massive telehealth uptake on end-user satisfaction","volume":"51","author":"Bate","year":"2021","journal-title":"Intern. Med. J."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ar, I., and Akgul, Y.S. (2013). A monitoring system for home-based physiotherapy exercises. Computer and Information Sciences III: 27th International Symposium on Computer and Information Sciences, Springer.","DOI":"10.1007\/978-1-4471-4594-3_50"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1080\/09638280500534937","article-title":"Extrinsic feedback for motor learning after stroke: What is the evidence?","volume":"28","author":"Wulf","year":"2006","journal-title":"Disabil. Rehabil."},{"key":"ref_7","first-page":"10","article-title":"Automatic Feedback For Physiotherapy Exercises Based on PoseNet","volume":"2","author":"Rakbah","year":"2020","journal-title":"Inf. Bull. Comput. Inf."},{"key":"ref_8","unstructured":"Ranasinghe, I., Dantu, R., Albert, M.V., Watts, S., and Ocana, R. (2021, January 17\u201321). Cyber-Physiotherapy: Rehabilitation to training. Proceedings of the 2021 IFIP\/IEEE International Symposium on Integrated Network Management (IM), Bordeaux, France."},{"key":"ref_9","first-page":"48","article-title":"Virtual Yoga System Using Kinect Sensor","volume":"9","author":"Wagh","year":"2022","journal-title":"Int. Res. J. Eng. Technol. (IRJET)"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Vallati, C., Virdis, A., Gesi, M., Carbonaro, N., and Tognetti, A. (2019). ePhysio: A wearables-enabled platform for the remote management of musculoskeletal diseases. Sensors, 19.","DOI":"10.3390\/s19010002"},{"key":"ref_11","first-page":"1290","article-title":"Yoga pose detection and correction using posenet and KNN","volume":"9","author":"Bhosale","year":"2022","journal-title":"Int. Res. J. Eng. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1007\/s10618-022-00895-4","article-title":"Fast and robust video-based exercise classification via body pose tracking and scalable multivariate time series classifiers","volume":"37","author":"Singh","year":"2023","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Singh, A., Le, B.T., Nguyen, T.L., Whelan, D., O\u2019Reilly, M., Caulfield, B., and Ifrim, G. (2021). Interpretable classification of human exercise videos through pose estimation and multivariate time series analysis. International Workshop on Health Intelligence, Springer.","DOI":"10.1007\/978-3-030-93080-6_14"},{"key":"ref_14","unstructured":"Raju, K. (2022). Exercise Detection and Tracking Using MediaPipe BlazePose and Spatial-Temporal Graph Convolutional Neural Network. [Ph.D. Dissertation, National College of Ireland]."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5269","DOI":"10.1007\/s11227-021-04076-w","article-title":"Development of a yoga posture coaching system using an interactive display based on transfer learning","volume":"78","author":"Long","year":"2022","journal-title":"J. Supercomput."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Bhamidipati, V.S.P., Saxena, I., Saisanthiya, D., and Retnadhas, M. (2023, January 5\u20136). Robust Intelligent Posture Estimation for an AI Gym Trainer using Mediapipe and OpenCV. Proceedings of the 2023 International Conference on Networking and Communications (ICNWC), Chennai, India.","DOI":"10.1109\/ICNWC57852.2023.10127264"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kramer, I., Schmidt, N., Memmesheimer, R., and Paulus, D. (2019, January 14\u201318). Evaluation of physical therapy through analysis of depth images. Proceedings of the 2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), New Delhi, India.","DOI":"10.1109\/RO-MAN46459.2019.8956435"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2452","DOI":"10.1109\/JBHI.2020.2999902","article-title":"Evaluation of machine learning models for classifying upper extremity exercises using inertial measurement unit-based kinematic data","volume":"24","author":"Hua","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Huang, C.-H., Lin, C.-F., Chen, C.-A., Hwang, C.-H., and Huang, D.-C. (2020, January 25\u201328). Real-time rehabilitation exercise performance evaluation system using deep learning and thermal image. Proceedings of the 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Dubrovnik, Croatia.","DOI":"10.1109\/I2MTC43012.2020.9129146"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"10424","DOI":"10.1007\/s11227-021-03684-w","article-title":"Novel side pose classification model of stretching gestures using three-layer LSTM","volume":"77","author":"Solongontuya","year":"2021","journal-title":"J. Supercomput."},{"key":"ref_21","first-page":"7","article-title":"Mono Camera-based Human Skeletal Tracking for Squat Exercise Abnormality Detection using Double Exponential Smoothing","volume":"13","author":"Muhammad","year":"2022","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_22","first-page":"1176","article-title":"Kinect-based physiotherapy and assessment: A comprehensive","volume":"11","author":"Rashid","year":"2018","journal-title":"Indones. J. Electr. Eng. Comput. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Siddique, T., Fareh, R., Abdallah, M., Ahmed, Z., and Rahman, M.H. (2022). Autonomous exercise generator for upper extremity rehabilitation: A fuzzy-logic-based approach. Micromachines, 13.","DOI":"10.3390\/mi13060842"},{"key":"ref_24","unstructured":"(2023, December 15). 2K QHD Webcam. Available online: https:\/\/www.eteknix.com\/hiievpu-2k-webcam\/."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Siddiqui, H.U.R., Saleem, A.A., Raza, M.A., Villar, S.G., Lopez, L.A.D., Diez, I.d.l.T., Rustam, F., and Dudley, S. (2023). Empowering lower limb disorder identification through PoseNet and artificial intelligence. Diagnostics, 13.","DOI":"10.3390\/diagnostics13182881"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2305","DOI":"10.1007\/s00371-022-02416-2","article-title":"Flow-pose Net: An effective two-stream network for fall detection","volume":"39","author":"Fei","year":"2023","journal-title":"Vis. Comput."},{"key":"ref_27","unstructured":"(2023, December 15). MediaPipe Solutions Guide. Available online: https:\/\/developers.google.com\/mediapipe\/solutions\/guide."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chen, Y., Shen, C., Wei, X.-S., Liu, L., and Yang, J. (2017, January 22\u201329). Adversarial posenet: A structure-aware convolutional network for human pose estimation. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.137"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Bhati, B.S., and Rai, C.S. (2020). Ensemble based approach for intrusion detection using extra tree classifier. Intelligent Computing in Engineering: Select Proceedings of RICE 2019, Springer.","DOI":"10.1007\/978-981-15-2780-7_25"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_32","first-page":"3321","article-title":"LGBM: A machine learning approach for Ethereum fraud detection","volume":"14","author":"Aziz","year":"2022","journal-title":"Int. J. Inf. Technol."},{"key":"ref_33","unstructured":"Guryanov, A. (2019). Histogram-based algorithm for building gradient boosting ensembles of piecewise linear decision trees. Analysis of Images, Social Networks and Texts: 8th International Conference, AIST 2019, Kazan, Russia, 17\u201319 July 2019, Revised Selected Papers 8, Springer."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/19\/6325\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:07:07Z","timestamp":1760112427000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/19\/6325"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"references-count":33,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["s24196325"],"URL":"https:\/\/doi.org\/10.3390\/s24196325","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,29]]}}}