{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T10:54:59Z","timestamp":1791284099075,"version":"4.1.0"},"reference-count":42,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"MSIT (Ministry of Science and ICT), Korea"},{"name":"ITRC (Information Technology Research Center) support program","award":["IITP-2024-RS-2024-00437191"],"award-info":[{"award-number":["IITP-2024-RS-2024-00437191"]}]},{"name":"IITP"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To introduce and evaluate an efficient neural network approach for human pose estimation and correction during physical therapy exercises using wearable sensor data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We leveraged benchmark data consisting of 276,625 records from wearable inertial and magnetic sensors. A novel method termed Random Forest Long Short-Term Memory (RFL), which integrates long short-term memory and Random Forest neural networks, was implemented for transfer feature engineering. The smartphone sensor data was used to generate new temporal and probabilistic features. These features were then utilized in machine learning methods to classify physical therapy exercises. Rigorous experiments, including k-fold validation and hyperparameter optimization, were conducted to validate the performance of the RFL approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The RFL approach demonstrated superior performance, achieving a remarkable 99% accuracy with the Random Forest method. The rigorous experiments confirmed the efficacy and reliability of the method in classifying physical therapy exercises.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed RFL method introduces a novel feature generation approach enhancing the accuracy of physical therapy exercise classification and correction. This innovative integration not only improves rehabilitation monitoring but also paves the way for more adaptive and intelligent physiotherapy assistance systems. By leveraging sensor data and advanced machine learning techniques, it has the potential to mitigate risks associated with disabilities and major diseases, thereby offering a feasible alternative to frequent clinic visits for consistent therapist guidance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.7717\/peerj-cs.2854","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T04:40:28Z","timestamp":1745901628000},"page":"e2854","source":"Crossref","is-referenced-by-count":9,"title":["Human pose estimation in physiotherapy fitness exercise correction using novel transfer learning approach"],"prefix":"10.7717","volume":"11","author":[{"given":"Aisha","family":"Naseer","sequence":"first","affiliation":[{"name":"Institute of Information Technology, Khwaja Fareed University of Engineering & Information Technology, Rahim Yar Khan, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5429-9835","authenticated-orcid":true,"given":"Ali","family":"Raza","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, University of Lahore, Lahore, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hadeeqa","family":"Afzal","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, Khwaja Fareed University of Engineering & Information Technology, Rahim Yar Khan, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aseel","family":"Smerat","sequence":"additional","affiliation":[{"name":"Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India"},{"name":"Computer Technologies Engineering, Mazaya University College, Nasiriyah, Iraq"},{"name":"Faculty of Educational Sciences, Al-Ahliyya Amman University, Amman, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1133-3965","authenticated-orcid":true,"given":"Norma Latif","family":"Fitriyani","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence and Data Science, Sejong University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0002-9386","authenticated-orcid":true,"given":"Yeonghyeon","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence and Data Science, Sejong University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5640-4413","authenticated-orcid":true,"given":"Muhammad","family":"Syafrudin","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence and Data Science, Sejong University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"key":"10.7717\/peerj-cs.2854\/ref-1","first-page":"263","article-title":"Accelerating hyperparameter tuning of a deep learning model for remote sensing image classification","author":"Aach","year":"2022"},{"key":"10.7717\/peerj-cs.2854\/ref-2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-94463-0","volume-title":"Neural networks and deep learning: a textbook","author":"Aggarwal","year":"2018"},{"key":"10.7717\/peerj-cs.2854\/ref-3","first-page":"17","article-title":"Cross validation configuration on K-NN for finger movements using EMG signals","author":"Anam","year":"2021"},{"issue":"1","key":"10.7717\/peerj-cs.2854\/ref-4","doi-asserted-by":"publisher","first-page":"2436946","DOI":"10.1155\/2022\/2436946","article-title":"Gaussian na\u00efve Bayes algorithm: a reliable technique involved in the assortment of the segregation in cancer","volume":"2022","author":"Anand","year":"2022","journal-title":"Mobile Information Systems"},{"key":"10.7717\/peerj-cs.2854\/ref-5","doi-asserted-by":"publisher","DOI":"10.24432\/C5JK60","article-title":"Physical therapy exercises dataset","author":"Aras","year":"2022"},{"issue":"1","key":"10.7717\/peerj-cs.2854\/ref-6","doi-asserted-by":"publisher","first-page":"363","DOI":"10.3390\/s23010363","article-title":"Physiotherapy exercise classification with single-camera pose detection and machine learning","volume":"23","author":"Arrowsmith","year":"2022","journal-title":"Sensors"},{"key":"10.7717\/peerj-cs.2854\/ref-7","doi-asserted-by":"publisher","first-page":"111598\u2013111607","DOI":"10.1109\/ACCESS.2023.3323592","article-title":"Comparative performance analysis of machine learning algorithms for arm and shoulder exercises using wrist-worn band","volume":"11","author":"Asghar","year":"2023","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.2854\/ref-8","first-page":"1","article-title":"A video analysis system using K-nearest neighbour algorithm for error detection in squat form","author":"Bansal","year":"2023"},{"issue":"13","key":"10.7717\/peerj-cs.2854\/ref-9","doi-asserted-by":"publisher","first-page":"2027","DOI":"10.3390\/math12132027","article-title":"Three-dimensional vehicle detection and pose estimation in monocular images for smart infrastructures","volume":"12","author":"Borau Bernad","year":"2024","journal-title":"Mathematics"},{"key":"10.7717\/peerj-cs.2854\/ref-10","doi-asserted-by":"publisher","first-page":"61677","DOI":"10.1109\/ACCESS.2018.2874767","article-title":"Performance analysis of google colaboratory as a tool for accelerating deep learning applications","volume":"6","author":"Carneiro","year":"2018","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.2854\/ref-11","first-page":"143","article-title":"Automatic evaluation of physiotherapy activities using deep learning techniques","author":"Carrera","year":"2022"},{"issue":"3","key":"10.7717\/peerj-cs.2854\/ref-12","doi-asserted-by":"publisher","first-page":"203","DOI":"10.36909\/jer.v8i3.6523","article-title":"Design of arm exercises for rehabilitation assistance","volume":"8","author":"Chaparro-Rico","year":"2020","journal-title":"Journal of Engineering Research"},{"key":"10.7717\/peerj-cs.2854\/ref-13","first-page":"44","article-title":"Comprehensive performance evaluation of intrusion detection model based on radar chart method","author":"Chen","year":"2022"},{"key":"10.7717\/peerj-cs.2854\/ref-14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2008.13567","article-title":"Introduction to logistic regression","author":"Chung","year":"2020"},{"issue":"5","key":"10.7717\/peerj-cs.2854\/ref-15","doi-asserted-by":"publisher","first-page":"395","DOI":"10.3390\/arm92050037","article-title":"Secure and transparent lung and colon cancer classification using blockchain and Microsoft azure","volume":"92","author":"Eliwa","year":"2024","journal-title":"Advances in Respiratory Medicine"},{"issue":"15","key":"10.7717\/peerj-cs.2854\/ref-16","doi-asserted-by":"publisher","first-page":"6727","DOI":"10.3390\/s23156727","article-title":"Innovative hybrid approach for masked face recognition using pretrained mask detection and segmentation, robust PCA, and KNN classifier","volume":"23","author":"Eman","year":"2023","journal-title":"Sensors"},{"key":"10.7717\/peerj-cs.2854\/ref-17","article-title":"Heart failure prediction dataset. Kaggle","author":"Fedesoriano","year":"2024"},{"key":"10.7717\/peerj-cs.2854\/ref-18","doi-asserted-by":"publisher","first-page":"2174","DOI":"10.1109\/TNSRE.2022.3226459","article-title":"Computer vision based on a modular neural network for automatic assessment of physical therapy rehabilitation activities","volume":"31","author":"Francisco","year":"2023","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"issue":"9868","key":"10.7717\/peerj-cs.2854\/ref-19","doi-asserted-by":"publisher","first-page":"104939","DOI":"10.1016\/j.knosys.2019.104939","article-title":"Assessing physical activity and functional fitness level using convolutional neural networks","volume":"185","author":"Gal\u00e1n-Mercant","year":"2019","journal-title":"Knowledge-Based Systems"},{"issue":"13","key":"10.7717\/peerj-cs.2854\/ref-20","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.3390\/math12131955","article-title":"Novel ensemble learning algorithm for early detection of lower back pain using spinal anomalies","volume":"12","author":"Haider","year":"2024","journal-title":"Mathematics"},{"key":"10.7717\/peerj-cs.2854\/ref-21","first-page":"278","article-title":"Random decision forests","volume":"1","author":"Ho","year":"1995"},{"issue":"1\u20132","key":"10.7717\/peerj-cs.2854\/ref-22","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.promfg.2020.04.090","article-title":"Machine learning based activity recognition to identify wasteful activities in production","volume":"45","author":"Hofmann","year":"2020","journal-title":"Procedia Manufacturing"},{"issue":"13","key":"10.7717\/peerj-cs.2854\/ref-23","doi-asserted-by":"publisher","first-page":"7487","DOI":"10.3390\/app13137487","article-title":"Effective quantization evaluation method of functional movement screening with improved gaussian mixture model","volume":"13","author":"Hong","year":"2023","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.2854\/ref-24","first-page":"1","article-title":"Attention-guided deep learning framework for movement quality assessment","author":"Kanade","year":"2023"},{"key":"10.7717\/peerj-cs.2854\/ref-25","first-page":"218","article-title":"Recognizing physiotherapy exercises using machine learning","author":"Kanungo","year":"2023"},{"issue":"4","key":"10.7717\/peerj-cs.2854\/ref-26","doi-asserted-by":"publisher","first-page":"2139","DOI":"10.47611\/jsrhs.v10i4.2139","article-title":"Design of a physical therapy device for lower leg recovery","volume":"10","author":"Khemani","year":"2021","journal-title":"Journal of Student Research"},{"key":"10.7717\/peerj-cs.2854\/ref-27","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1002\/acr.24439","article-title":"Challenges with strengthening exercises for people with knee osteoarthritis and comorbid obesity: a qualitative study with patients and physical therapists","volume":"50","author":"Lawford","year":"2020","journal-title":"Internal Medicine Journal"},{"issue":"2","key":"10.7717\/peerj-cs.2854\/ref-28","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1109\/TNSRE.2020.2966249","article-title":"A deep learning framework for assessing physical rehabilitation exercises","volume":"28","author":"Liao","year":"2020","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"10.7717\/peerj-cs.2854\/ref-29","first-page":"1","article-title":"Wearable-based frozen shoulder rehabilitation exercise recognition using machine learning approaches","author":"Liu","year":"2023"},{"key":"10.7717\/peerj-cs.2854\/ref-30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2108.01375","article-title":"Classifying action correctness in physical rehabilitation exercises","author":"Miron","year":"2021"},{"issue":"1","key":"10.7717\/peerj-cs.2854\/ref-31","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1186\/s40537-024-00944-3","article-title":"Feature reduction for hepatocellular carcinoma prediction using machine learning algorithms","volume":"11","author":"Mostafa","year":"2024","journal-title":"Journal of Big Data"},{"key":"10.7717\/peerj-cs.2854\/ref-32","first-page":"335","article-title":"End-user programming architecture for physical movement assessment: an interactive machine learning approach","author":"Palomares-Pecho","year":"2020"},{"key":"10.7717\/peerj-cs.2854\/ref-33","doi-asserted-by":"publisher","first-page":"138457\u2013138471","DOI":"10.1109\/ACCESS.2023.3340304","article-title":"Preventing road accidents through early detection of driver behavior using smartphone motion sensor data: an ensemble feature engineering approach","volume":"11","author":"Raza","year":"2023","journal-title":"IEEE Access"},{"issue":"3","key":"10.7717\/peerj-cs.2854\/ref-34","doi-asserted-by":"publisher","first-page":"71326","DOI":"10.1109\/ACCESS.2023.3294542","article-title":"Transfer learning-based smart features engineering for osteoarthritis diagnosis from knee X-ray images","volume":"11","author":"Rehman","year":"2023","journal-title":"IEEE Access"},{"issue":"6","key":"10.7717\/peerj-cs.2854\/ref-35","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.3390\/math11061449","article-title":"Optimal robot pose estimation using scan matching by turning function","volume":"11","author":"Sadeghi Bigham","year":"2023","journal-title":"Mathematics"},{"issue":"10","key":"10.7717\/peerj-cs.2854\/ref-36","doi-asserted-by":"publisher","first-page":"pzad126","DOI":"10.1093\/ptj\/pzad126","article-title":"Research Agenda for physical therapy from the American physical therapy association","volume":"103","author":"Stevens-Lapsley","year":"2023","journal-title":"Physical Therapy"},{"issue":"3","key":"10.7717\/peerj-cs.2854\/ref-37","doi-asserted-by":"publisher","first-page":"25","DOI":"10.21608\/sjdfs.2023.222524.1117","article-title":"A novel hybrid approach to masked face recognition using robust PCA and GOA optimizer","volume":"13","author":"Taha","year":"2023","journal-title":"Scientific Journal for Damietta Faculty of Science"},{"key":"10.7717\/peerj-cs.2854\/ref-38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.10325","article-title":"Classifying human activities using machine learning and deep learning techniques","author":"Uday","year":"2022"},{"key":"10.7717\/peerj-cs.2854\/ref-39","first-page":"2657","article-title":"Accelerometer based classification of elbow flexion and extension exercises","author":"Uslu","year":"2020"},{"issue":"1","key":"10.7717\/peerj-cs.2854\/ref-40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-007-0114-2","article-title":"Top 10 algorithms in data mining","volume":"14","author":"Wu","year":"2008","journal-title":"Knowledge and Information Systems"},{"issue":"2","key":"10.7717\/peerj-cs.2854\/ref-41","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.cmpb.2014.07.003","article-title":"Automated evaluation of physical therapy exercises using multi-template dynamic time warping on wearable sensor signals","volume":"117","author":"Yurtman","year":"2014","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"10.7717\/peerj-cs.2854\/ref-42","doi-asserted-by":"publisher","first-page":"77561","DOI":"10.1109\/ACCESS.2020.2989128","article-title":"Rehabilitation exercise recognition and evaluation based on smart sensors with deep learning framework","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-2854.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2854.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2854.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2854.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T04:40:41Z","timestamp":1745901641000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-2854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,29]]},"references-count":42,"alternative-id":["10.7717\/peerj-cs.2854"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.2854","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,29]]},"article-number":"e2854"}}