Citation

Arnumukti, Mahda Laina and Yunus, Andi Prademon and Babale, Aliyu Suleiman (2025) Improve Exercise Movement: Detecting Mistakes on Yoga with Mediapipe and MLP. International Journal on Robotics, Automation and Sciences, 7 (1). pp. 64-71. ISSN 2682-860X

Text View of Improve Exercise Movement_ Detecting Mistakes on Yoga with Mediapipe and MLP.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

Yoga is known as a comprehensive hone for keeping up physical and mental health. Be that as it may, improper execution of yoga poses 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, down dog, goddess, warrior, and plank. Experimental results show that the model achieved 98% accuracy during training, but accuracy during testing decreased to 95%. This appears an sign of overfitting, where the demonstrate adjusts as well much to the preparing information and is less able to generalize to the test information. 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 legitimately and anticipate wounds.

Item Type:	Article
Uncontrolled Keywords:	Yoga
Subjects:	B Philosophy. Psychology. Religion > BF Psychology (General) > BF1001-1389 Parapsychology
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	26 Jun 2025 01:20
Last Modified:	26 Jun 2025 01:20
URII:	http://shdl.mmu.edu.my/id/eprint/14067

Downloads

Edit (login required)