Haluvarthi Prabhudeva, Chandana (2023) Deep Learning for Automated Yoga Practice Assistance. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (3MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (795kB) | Preview |
Abstract
The study focuses on the relationship between technology and traditional practices, focuses on the classification of yoga poses using artificial intelligence (AI) and deep learning techniques like convolutional neural networks (CNNs). This research aims to apply AI to enhance yoga knowledge and practice while considering the physical and mental health advantages of yoga. The study’s primary objective was to develop a deep learning model that could accurately identify various yoga poses from images. In order to achieve this, pre-trained CNN models like VGG16, ResNet50, and MobileNetV2 were modified with the intention of identifying yoga positions. As part of the study, the architecture and layout of multiple models were examined to determine which was most effective in achieving this objective. One of the most significant findings is that the MobileNetV2 model demonstrated effective learning and adaptation to the particular limitations of yoga position categorization, achieving 100% training accuracy and up to 87.65% validation accuracy after ten training epochs. In contrast, however promising, the validation accuracies of the VGG16 and ResNet50 models were somewhat lower, at 86.42% and 73.46%, respectively. These results highlight the potential and challenges of applying AI to the classification of complex human postures, including yoga poses.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Jain, Mayank UNSPECIFIED |
Subjects: | G Geography. Anthropology. Recreation > GV Recreation Leisure Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning R Medicine > RA Public aspects of medicine > RA790 Mental Health |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Ciara O'Brien |
Date Deposited: | 08 May 2025 15:48 |
Last Modified: | 08 May 2025 15:48 |
URI: | https://norma.ncirl.ie/id/eprint/7524 |
Actions (login required)
![]() |
View Item |