Authors : Dr. N. Usha Rani; Ruhi Farhath Siddavatam; Illuru Anwar; Pilimitla Jhansi

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/y24kpj63

Scribd : https://tinyurl.com/55ye64nm

DOI : https://doi.org/10.38124/ijisrt/25apr2276

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The evolution of yoga has been remarkable and beneficial over the years as it is a discipline focused on an individual’s physical, mental, and overall emotional well-being. It is very common in today's world but still follows a traditional one-size-fits-all method. This can be problematic as it does not accommodate the broad range of diverse individual per practitioner’s health conditions, limitations, or needs. To address that, our current work presents XAI Yoga Guru, a personalized yoga pose suggesting system that uses Machine Learning, Explainable Artificial Intelligence (XAI) and Retrieval-Augmented Generation (RAG). The system gathers a user’s medical information along with their preferences and suggests unique yoga poses fit for their requirements. Most importantly, each recommendation given is accompanied by an interpretable explanation that shows why the recommendation was made, which improves user trust, safety, and understanding. The blend of personalization with explainability enables users to practice yoga more safely while helping them achieve their wellness goals effectively. The approach taken XAI alongside yoga shows there is a possibility of developing new advanced technologies in wellness catered for specific users’ needs.

Keywords : Machine Learning, Explainable AI (XAI), Retrieval-Augmented Generation (RAG), Streamlit.

References :

1. R. Kaur and A. Sharma, “Yoga Pose Recognition and Correction Using Computer Vision Techniques,” in Procedia Computer Science, vol. 132, pp. 1710–1717, 2018.
2. Tiwari and S. Malhotra, “Personalized Yoga Recommendations Using Machine Learning               Techniques,” in International Journal of Computer Applications, vol. 182, no. 45, pp. 20–26, 2019.
3. S. Patel and R. Desai, “Evaluating the Personalization Gaps in Health and Fitness Mobile Applications,” in Journal of Medical Internet Research, vol. 22, no. 7, pp. e16522, 2020.
4. M. Ribeiro, S. Singh, and C. Guestrin, “Why Should I Trust You?: Explaining the Predictions of Any Classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144, 2016.
5. P. Lewis, E. Perez, A. Piktus, et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 9459–9474, 2020.
6. L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
7. Doshi-Velez and B. Kim, “Towards a Rigorous Science of Interpretable Machine Learning,” arXiv preprint, arXiv:1702.08608, 2017