Improve Exercise Movement: Detecting Mistakes on Yoga with Mediapipe and MLP

Article Sidebar

PDF
Published: Mar 31, 2025
DOI: https://doi.org/10.33093/ijoras.2025.7.1.8
Keywords:
Exercise Analysis, Mediapipe, MLP, Yoga

Main Article Content

Mahda Laina Arnumukti
Faculty of Informatics, Telkom University (Indonesia)
https://orcid.org/0009-0001-5197-6834
Andi Prademon Yunus
Faculty of Informatics, Telkom University (Indonesia)
Babale Aliyu Suleiman
Department of Electrical Engineering, Bayero University Kano (Nigeria)

Abstract

Yoga is known as a comprehensive practice for maintaining physical and mental health. However, improper execution of yoga postures can cause injury, hinder progress, and potentially damage health. To overcome this problem, this research utilizes Mediapipe as a data preprocessing tool to identify yoga poses, which are then classified using the Multi-Layer Perceptron (MLP) algorithm. In the process, data normalization is carried out to increase prediction accuracy. This research uses a dataset consisting of six classes of yoga poses, namely tree, downdog, goddess, warrior, and plank. Experimental results show that the model achieved 98% accuracy during training, but accuracy during testing decreased to 95%. This shows an indication of overfitting, where the model adapts too much to the training data and is less able to generalize to the test data. This study makes an important contribution to the development of a safer and more accurate yoga pose classification system, which can be applied to practice yoga properly and prevent injuries.
 
Manuscript received: 15 Oct 2024 | Revised: 30 Jan 2025 | Accepted: 11 Feb 2025 | Published: 31 Mar 2025

Article Details

How to Cite
Arnumukti, M. L. ., Yunus, A. P. Y., & Babale, A. S. (2025). Improve Exercise Movement: Detecting Mistakes on Yoga with Mediapipe and MLP. International Journal on Robotics, Automation and Sciences, 7(1), 64–71. https://doi.org/10.33093/ijoras.2025.7.1.8
Issue
Vol. 7 No. 1 (2025): International Journal on Robotics, Automation and Sciences
Section
Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

References

R. Garg, S., Saxena, A. & Gupta, “Yoga pose classification: a CNN and MediaPipe inspired deep learning approach for real-world application,” Journal of Ambient Intelligence and Humanized Computing, 2022.

DOI:https://doi.org/10.1007/s12652-022-03910-0

K. Kundu and A. Goswami, "Classification of Yoga Poses Using Integration of Deep Learning and Machine Learning Techniques," Lecture Notes in Networks and Systems, pp. 417-428, 2023.

DOI: https://doi.org/10.1007/978-981-19-8825-7_36

H. Dhakate, S. Anasane, S. Shah, R. Thakare and S.G. Rawat, "Enhancing Yoga Practice: Real-time Pose Analysis and Personalized Feedback," 2024 International Conference on Emerging Systems and Intelligent Computing (ESIC), pp. 35-40, 2024.

DOI: https://doi.org/10.1109/esic60604.2024.10481659

C. C. Lim, K. S. Sim, and C. K. Toa, "Development of visual-based rehabilitation using sensors for stroke patient,” International Journal on Robotics, Automation and Sciences, vol. 2, no. 1, pp. 22–27, 2020.

DOI: https://doi.org/10.33093/ijoras.2020.2.4

Z. Y. Lim, T. C. Khim, R. Edwin, and K. S. Sim, "Development of augmented reality based applications for brain memory training," International Journal on Robotics, Automation and Sciences, vol. 5, no. 1, pp. 13–20, 2023.

DOI: https://doi.org/10.33093/ijoras.2023.5.1.3

G. Tierney, "Concussion biomechanics, head acceleration exposure and brain injury criteria in sport: a review," Sports Biomechanics, pp. 1-29, 2021.

DOI: https://doi.org/10.1080/14763141.2021.2016929

U. Dedhia, P. Bhoir, P. Ranka and P. Kanani, "Pose Estimation and Virtual Gym Assistant Using MediaPipe and Machine Learning," 2023 International Conference on Network, Multimedia and Information Technology (NMITCON), pp. 1-7, 2023.

DOI: https://doi.org/10.1109/NMITCON58196.2023.10275938

H.Y. Ting, K.S. Sim, and F.S. Abas, “Kinect-Based Badminton Action Analysis System,” Advanced Materials Research, pp. 94–99, 2014.

DOI: https://doi.org/10.4028/www.scientific.net/amr.1042.94

A.P. Yunus, K. Morita, N.C. Shirai and T. Wakabayashi, "Time Series Self-Attention Approach for Human Motion Forecasting: A Baseline 2D Pose Forecasting," Journal of Advanced Computational Intelligence and Intelligent Informatics, vol. 27, no. 3, pp. 445-457, 2023.

DOI: https://doi.org/10.20965/jaciii.2023.p0445

R. G. Candraningtyas, A. P. Yunus, and Y. H. Choo, "Human fall motion prediction: A review," International Journal on Robotics, Automation and Sciences, vol. 6, no. 2, pp. 52–58, 2024.

DOI: https://doi.org/10.33093/ijoras.2024.6.2.8

R. G. Garg, Shubham, Aman Saxena, “Yoga pose classification: a CNN and MediaPipe inspired deep learning approach for real-world application,” Journal of Ambient Intelligence and Humanized Computing, vol. 14, 2022.

DOI: https://doi.org/10.1007/s12652-022-03910-0

V. A. Aydin, “Comparison of CNN-based methods for yoga pose classification.,” Turkish Journal of Engineering (TUJE), vol. 8, no. 1, 2024.

DOI: https://doi.org/10.31127/tuje.1275826

R. Makhijani, S. Sagar, K.B.P. Reddy, S.K. Mourya, J.S. Krishna and M.M. Kulkarni, "Yoga Pose Rectification Using Mediapipe and Catboost Classifier," Lecture Notes in Networks and Systems, pp. 379-387, 2023.

DOI: https://doi.org/10.1007/978-981-19-7867-8_30

A. Chelladurai, D. L. Narayan, P. B. Divakarachari, and U. Loganathan, “fMRI-Based Alzheimer’s Disease Detection Using the SAS Method with Multi-Layer Perceptron Network,” Brain Sciences, vol. 13, no. 6, 2023.

DOI: https://doi.org/10.3390/brainsci13060893

V.S.P. Bhamidipati, I. Saxena, D. Saisanthiya and M. Retnadhas, "Robust Intelligent Posture Estimation for an AI Gym Trainer using Mediapipe and OpenCV," 2023 International Conference on Networking and Communications (ICNWC), 2023.

DOI: https://doi.org/10.1109/ICNWC57852.2023.10127264

D. Parashar, O. Mishra, K. Sharma, and A. Kukker, “Improved Yoga Pose Detection Using MediaPipe and MoveNet in a Deep Learning Model,” Revue d’Intelligence Artificielle, vol. 37, no. 5, pp. 1197–1202, 2023.

DOI: https://doi.org/10.18280/ria.370511

W. X. Lim, C. K. Toa, and K. S. Sim, “The application of augmented reality platform for chemistry learning,” International Journal on Robotics, Automation and Sciences, vol. 5, no. 2, pp. 101–110, 2023.

DOI: https://doi.org/10.33093/ijoras.2023.5.2.13

Q. Hou, Z. Jiang, L. Yuan, M. Cheng, S. Yan and J. Feng, "Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, pp. 1328-1334, 2023.

DOI: https://doi.org/10.1109/TPAMI.2022.3145427

C. H. Chen, K. B. Gan, and N. A. A. Aziz, “Upper Limbs Extension and Flexion Angles Calculation and Visualization Using Two Wearable Inertial Measurement Units,” International Journal on Robotics, Automation and Sciences, vol. 4, pp. 1–7, 2022.

DOI: https://doi.org/10.33093/ijoras.2022.4.1