Integrating Generative AI for Enhanced Fitness Coaching: From Exercise form to Posture and Body Composition Analysis
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".