Integrating Generative AI for Enhanced Fitness Coaching: From Exercise form to Posture and Body Composition Analysis
Li, Jiaye Abouzahir, Saad El Saddik, Abdulmotaleb
Li, Jiaye
Abouzahir, Saad
El Saddik, Abdulmotaleb
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Recently, several applications and specialized versions of ChatGPT have been developed to either create personalized exercise programs based on the fitness levels of practitioners or to provide post-exercise nutrition and recovery advice. However, existing specialized ChatGPTs are limited to specific tasks, and not well-finetuned. In this paper, we introduce a novel application of ChatGPT as a personalized assistant capable of correcting improper postures and analyzing body compositions. We trained ChatGPT to improve posture during exercises and daily activities, thereby enhancing its role as an assistant to prevent injuries and optimize training effectiveness. In addition, we explore ChatGPT's potential to understand body compositions and predict physical transformations, providing users with insights into the outcomes of their fitness and nutrition efforts. Our results indicate that the current ChatGPT model can identify and correct incorrect postures, but struggles to provide visual aids for the correction. It can also provide training schedules and nutrition plans based on requirements, but those plans tend to be general and lack customization. In terms of body composition, ChatGPT can analyze body fat on a broader scale, but with less sensitivity to smaller changes in body fat. The performance of ChatGPT can be further improved using more image datasets related to gym exercises, human postures, and body compositions.
Citation
J. Li, S. Abouzahir and A. El Saddik, "Integrating Generative AI for Enhanced Fitness Coaching: From Exercise form to Posture and Body Composition Analysis," 2025 IEEE Medical Measurements & Applications (MeMeA), Chania, Greece, 2025, pp. 1-5, doi: 10.1109/MeMeA65319.2025.11068068
Source
2025 IEEE Medical Measurements & Applications
Conference
IEEE Medical Measurements & Applications (MeMeA)
Keywords
Generative AI, Large Language Model, Fitness Coaching, Posture Analysis, Well-being
Subjects
Source
IEEE Medical Measurements & Applications (MeMeA)
Publisher
IEEE