EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human pose estimation in physiotherapy fitness exercise correction using novel transfer learning approach

Aisha Naseer, Ali Raza iD, Hadeeqa Afzal, Aseel Smerat, Norma Latif Fitriyani iD, Yeonghyeon Gu iD, Muhammad Syafrudin iD

PeerJ Computer Science · 29.04.2025 · 11 · e2854

DOI: 10.7717/peerj-cs.2854 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 29.04.2025. Verfasst von Aisha Naseer und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information Technology, Khwaja Fareed University of Engineering & Information Technology, Rahim Yar Khan, Pakistan. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MSIT (Ministry of Science and ICT), Korea, ITRC (Information Technology Research Center) support program, IITP.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To introduce and evaluate an efficient neural network approach for human pose estimation and correction during physical therapy exercises using wearable sensor data.

Methods

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.

Results

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.

Conclusions

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.

Schlagwörter

Stichwörter der Autor:innen

Deep learningHuman pose estimationMachine learningPhysiotherapy Fitness ExerciseTransfer learning

Autor:innen und Institutionen

  • Institute of Information Technology, Khwaja Fareed University of Engineering & Information Technology, Rahim Yar Khan, Pakistan.
  • Department of Software Engineering, University of Lahore, Lahore, Pakistan.
  • Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India.
  • Computer Technologies Engineering, Mazaya University College, Nasiriyah, Iraq.
  • Faculty of Educational Sciences, Al-Ahliyya Amman University, Amman, Jordan.
  • Department of Artificial Intelligence and Data Science, Sejong University, Seoul, South Korea.

ORCID-Profile: Ali Raza, Norma Latif Fitriyani, Yeonghyeon Gu, Muhammad Syafrudin

Förderung

  • MSIT (Ministry of Science and ICT), Korea
  • ITRC (Information Technology Research Center) support program
  • IITP

Zitieren

APA

Naseer, A., Raza, A., Afzal, H., Smerat, A., Fitriyani, N. L., Gu, Y., & Syafrudin, M. (2025). Human pose estimation in physiotherapy fitness exercise correction using novel transfer learning approach. PeerJ Computer Science, 11, e2854. https://doi.org/10.7717/peerj-cs.2854

Vancouver

Naseer A, Raza A, Afzal H, Smerat A, Fitriyani NL, Gu Y, et al. Human pose estimation in physiotherapy fitness exercise correction using novel transfer learning approach. PeerJ Computer Science. 2025;11:e2854. doi:10.7717/peerj-cs.2854

BibTeX
@article{Naseer2025,
  author = {Naseer, Aisha and Raza, Ali and Afzal, Hadeeqa and Smerat, Aseel and Fitriyani, Norma Latif and Gu, Yeonghyeon and Syafrudin, Muhammad},
  title = {Human pose estimation in physiotherapy fitness exercise correction using novel transfer learning approach},
  journal = {PeerJ Computer Science},
  year = {2025},
  volume = {11},
  pages = {e2854},
  doi = {10.7717/peerj-cs.2854}
}
Kostenlos starten →