TARU PUBLICATIONS
Journal of Information and Optimization Sciences cover

Journal of Information and Optimization Sciences

(Since 1980)
Hybrid ·Peer-reviewed·ISSN (Online): 2169-0103·ISSN (Print): 0252-2667

WoS  JIF 2026 : 0.4 (Q4)

Powered by:Powered by

Monthly Journal: Publishes theoretical and applied research on topics in information and optimization sciences.

Issues up to 2022 co-published with and available at:Taylor & Francis
submissions@tarupublications.com
Taru Online First Current IssueSpecial IssuesBrowse all Issues
Journal of Information and Optimization Sciences
Open Access Research Article

Enhancing wellness through AI-powered yoga assistant : A human activity recognition application

, , , , , * , ,

* Corresponding author · click or hover a name for details

pp. 143–155Vol. 46Issue 1January 2025DOI: 10.47974/JIOS-1859XML
Received:
13 Aug 2024
Published Online:
19 Feb 2025
Article type:
Research Article
Language:
EN
Article no.:
JIOS-1859
Pages:
143–155

Abstract

Prioritizing health is crucial, yet it remains unfulfilled and requires increased attention. To address this issue, an automated artificial intelligence (AI) application that monitors postures and actions during exercise would be highly beneficial. In the proposed article, we offer a remote AI powered yoga trainer. This trainer incorporates OpenCV for live image capture and processing, which helps in identifying the key poses. Advanced AI techniques, such as deep learning, have proven beneficial in monitoring applications. In the proposed article, we proposed three AI yoga trainer models using deep neural network (DNN), convolutional neural network (CNN), and multilayer perceptron (MLP) models. We evaluated the proposed model’s performance on a publicly available dataset sourced from Kaggle, where we focused on obtaining yoga pose images, as well as their captions. Data processing, which includes data cleaning and augmentation, is performed to ensure the diversity of the dataset. A carefully curated set of yoga poses, such as chair, cobra, and shoulder stand, helps to provide beginner-friendly and health-beneficial practices remotely, thereby preventing the neglect of physical health.

Keywords

HARYoga TrainerCNNDNNMLP

Subject Classifications

68T07

References

[1] J. Omotoyosi Adeyemi, “‘Enhancing Elderly Wellness through AI-Powered Yoga and Exercise Support Systems,’” Biomed. J. Sci. Tech. Res., vol. 54, no. 4 (Jan. 2024), doi: 10.26717/BJSTR.2024.54.008579.
[2] N. Gupta, S. K. Gupta, R. K. Pathak, V. Jain, P. Rashidi, and J. S. Suri, Human activity recognition in artificial intelligence framework: a narrative review, no. 0123456789. Springer Netherlands (2022).
[3] H. Ding, S. R. K. Bran, J. A. Paradiso, and H. W. M. H. Arif, “FEMO: A platform for free-weight exercise monitoring with RFIDs,” SenSys 2015 - Proc. 13th ACM Conf. Embed. Networked Sens. Syst., pp. 141–154 (2015), doi: 10.1145/2809695.2809708.
[4] R. R. Kanase, A. N. Kumavat, R. D. Sinalkar, and S. Somani, “Pose Estimation and Correcting Exercise Posture,” ITM Web Conf., vol. 40, p. 03031 (Aug. 2021), doi: 10.1051/itmconf/20214003031.
[5] W. Qi and A. Aliverti, “A multimodal wearable system for continuous and real-time breathing pattern monitoring during daily activity,” IEEE J. Biomed. Heal. Informatics, vol. 24, no. 8, pp. 2199–2207 (2020) doi: 10.1109/JBHI.2019.2963048.
[6] A. Shah, W. Patel, and H. Koyuncu, “Empowering healthcare innovation : IoT-enabled smart systems and deep learning for enhanced diabetic retinopathy in the telehealth landscape,” J. Interdiscip. Math., vol. 27, no. 2, pp. 355–367 (2024), doi: 10.47974/JIM-1836.
[7] T. Singh and D. K. Vishwakarma, “A deeply coupled ConvNet for human activity recognition using dynamic and RGB images,” Neural Comput. Appl., vol. 33, no. 1, pp. 469–485 (2021), doi: 10.1007/s00521-020-05018-y.
[8] J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and D. Darrell, “Long-Term Recurrent Convolutional Networks for Visual Recognition and Description,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 4, pp. 677–691 (2017), doi: 10.1109/TPAMI.2016.2599174.
[9] A. Abobakr, M. Hossny, and S. Nahavandi, “A skeleton-free fall detection system from depth images using random decision forest,” IEEE Syst. J., vol. 12, no. 3, pp. 2994–3005 (2018), doi: 10.1109/JSYST.2017.2780260.
[10] M. Sivalakshmi, K. R. Prasad, and C. S. Bindu, “Convolutional-based variational autoencoders for face privacy protection in video surveillance,” J. Discret. Math. Sci. Cryptogr., vol. 27, no. 4, pp. 1205–1214 (2024), doi: 10.47974/JDMSC-1975.
[11] B. Jo and S. Kim, “Comparative Analysis of OpenPose, PoseNet, and MoveNet Models for Pose Estimation in Mobile Devices,” Trait. du Signal, vol. 39, no. 1, pp. 119–124 (Feb. 2022), doi: 10.18280/ts.390111.

Views: 413Downloads: 77Citations: 0