Generative AI in Human Fitness: Wearable-Aware Personalized Coaching with Multimodal Intelligence

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 13 | 03 | Page :
By

Shubham Chandoo Gite,

Sneha Tirth,

  1. U.G Student, Department of Computer Engineering, Trinity College of Engineering and Research, Pune, Maharashtra, India
  2. Assistant Professor, Department of Computer Engineering, Trinity College of Engineering and Research, Pune, Maharashtra, India

Abstract

This review presents a practical architecture for applying large language models and multimodal artificial intelligence to human fitness while preserving the roles of wearable sensing, evidence-based exercise guidance and human oversight. The proposed system combines signals from smartwatches and other electronic sensors with user goals, schedules, training history and self-reported effort. The paper emphasizes that fitness generation should remain risk-aware: uncertain sensor data, pain, unusual symptoms and requests outside the scope of general fitness guidance require conservative responses or referral to an appropriate professional. Seven conceptual diagrams describe the end-to-end architecture, wearable signal chain, evidence-grounded generation pipeline, adaptive coaching cycle, safety gate, human-in-the-loop evaluation framework and wearable edge-cloud electronics architecture. Seven tables summarize system comparisons, sensing options, generative AI use cases, architecture components, safety controls, evaluation measures and an implementation roadmap. The topic is aligned with electrical and electronics engineering through physiological and inertial sensors, analog front ends, microcontrollers, wireless connectivity and edge processing, and with artificial intelligence and machine learning through activity recognition, context modeling, retrieval and language generation. The resulting framework is suitable for student research and early prototypes because it focuses on explainable system design, safe personalization and measurable evaluation rather than unnecessary model complexity.

Keywords: Generative artificial intelligence, human fitness, large language models, wearable sensors, personalized coaching, multimodal AI, retrieval-augmented generation

How to cite this article: Shubham Chandoo Gite, Sneha Tirth. Generative AI in Human Fitness: Wearable-Aware Personalized Coaching with Multimodal Intelligence. Recent Trends in Sensor Research & Technology. 2026; 13(03):-.
How to cite this URL: Shubham Chandoo Gite, Sneha Tirth. Generative AI in Human Fitness: Wearable-Aware Personalized Coaching with Multimodal Intelligence. Recent Trends in Sensor Research & Technology. 2026; 13(03):-. Available from: https://journals.stmjournals.com/rtsrt/article=2026/view=262414

References

  1. Lai X, Chen J, Lai Y, Huang S, Cai Y, Sun Z, et al. Using large language models to enhance exercise recommendations and physical activity in clinical and healthy populations: scoping review. JMIR Medical Informatics. 2025;13:e59309. doi: 10.2196/59309.
  2. Shin D, Hsieh G, Kim YH. PlanFitting: Personalized Exercise Planning with Large Language Model-driven Conversational Agent. arXiv preprint arXiv:2309.12555. 2023 Sep 22. doi: 10.48550/arXiv.2309.12555.
  3. Mantena S, Johnson A, Oppezzo M, Schütz N, Tolas A, Doijad R, et al. Fine-tuning LLMs in behavioral psychology for scalable health coaching. npj Cardiovascular Health. 2025;2:48. doi: 10.1038/s44325- 025-00083-5.
  4. Templin T, Perez MW, Sylvia S, Leek J, Sinnott-Armstrong N. Addressing 6 challenges in generative AI for digital health: a scoping review. PLOS Digital Health. 2024;3(5):e0000503. doi: 10.1371/journal.pdig.0000503.
  5. Tilton AK, Caplan BE, Cole BJ. Generative AI in consumer health: leveraging large language models for health literacy and clinical safety with a digital health framework. Front Digit Health. 2025;7:1616488. doi:10.3389/fdgth.2025.1616488.
  6. Cusack NM, Venkatraman PD, Raza U, Faisal A. Review—Smart Wearable Sensors for Health and Lifestyle Monitoring: Commercial and Emerging Solutions. ECS Sens Plus. 2024;3(1):017001. doi:10.1149/2754-2726/ad3561.
  7. Rashid N, Nemati E, Ahmed MY, Kuang J, Gao JA. MM-HAR: Multi-Modal Human Activity Recognition Using Consumer Smartwatch and Earbuds. Annu Int Conf IEEE Eng Med Biol Soc. 2023;2023:1-4. doi:10.1109/EMBC40787.2023.10340984.
  8. Piwek L, Ellis DA, Andrews S, Joinson A. The rise of consumer health wearables: promises and barriers. PLoS Medicine. 2016;13(2):e1001953. doi: 10.1371/journal.pmed.1001953.
  9. Nahum-Shani I, Smith SN, Spring BJ, Collins LM, Witkiewitz K, Tewari A, Murphy SA. Just-in-time adaptive interventions (JITAIs) in mobile health: key components and design principles for ongoing health behavior support. Annals of Behavioral Medicine. 2018;52(6):446–462. doi: 10.1007/s12160-016- 9830-8.
  10. Moor M, Banerjee O, Shakeri Hossein Abad Z, Krumholz HM, Leskovec J, Topol EJ, Rajpurkar P. Foundation models for generalist medical artificial intelligence. Nature. 2023;616:259–265. doi: 10.1038/s41586-023-05881-4.
  11. Singhal K, Azizi S, Tu T, Mahdavi SS, Wei J, Chung HW, et al. Large language models encode clinical knowledge. Nature. 2023;620:172–180. doi: 10.1038/s41586-023-06291-2.
  12. Lee P, Bubeck S, Petro J. Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine. N Engl J Med. 2023;388(13):1233-1239. doi:10.1056/NEJMsr2214184.
  13. Tabassi E. Artificial Intelligence Risk Management Framework (AI RMF 1.0). Gaithersburg (MD): National Institute of Standards and Technology; 2023. NIST AI 100-1. doi:10.6028/NIST.AI.100-1.
  14. World Health Organization. WHO guidelines on physical activity and sedentary behaviour. Geneva: World Health Organization; 2020. ISBN: 978-92-4-001512-8.
  15. World Health Organization. Ethics and governance of artificial intelligence for health: WHO guidance. Geneva: World Health Organization; 2021. ISBN: 978-92-4-002920-0.
  16. Umakanth AAM. Conversational GenAI agents in mobile health and fitness apps. World Journal of Advanced Engineering Technology and Sciences. 2025;15(3):1968–1980. doi: 10.30574/wjaets.2025.15.3.1100.
  17. Vahdati M, Gholizadeh Hamlabadi K, Laamarti F, Kumar D, El Saddik A. Digital twin AI fitness coach: an intelligent multi-agent system for personalized exercise guidance. In: Proceedings of the 1st International Workshop on Multi-Sensorial Media and Applications (MSMA ’25). Dublin, Ireland: Association for Computing Machinery; 2025. doi: 10.1145/3728485.3759171.
Ahead of Print Subscription Review Article
Volume 13
03
Received 19/10/2026
Accepted 02/11/2026
Published 03/11/2026
Publication Time 15 Days

Login

My IP

PlumX Metrics

Support