Flexi-Fit: AI-Based Fitness Tracker
This paper introduces a personalized AI-based fitness tracker that provides dynamic diet and workout recommendations using the MERN stack, Llama 3 for natural language processing (NLP), and Hugging Face for machine learning. The tracker collects user-specific data such as dietary preferences, physical activity, and fitness goals to provide tailored suggestions. The NLP engine enables conversational interaction with users, making the system more intuitive and accessible. By integrating AI-powered insights and real-time data analysis, the system adapts to the user's progress and adjusts recommendations accordingly. This paper presents the architecture, methodology, and advantages of using such a system in a health and fitness context, demonstrating its potential to improve user fitness outcomes through precise interventions.
Authors
- Sameer Trivedi (ORCID: https://orcid.org/0000-0001-8308-9220)
- Amit Bhardwaj (ORCID: https://orcid.org/0000-0002-0172-2027)
- Vibha Jaiswal (ORCID: https://orcid.org/0000-0001-5407-7052)
- Abhilasha Singh (ORCID: https://orcid.org/0000-0002-9482-3141)
- Vishal Verma (ORCID: https://orcid.org/0000-0002-7442-4215)
Institutions
- SRM Institute of Science and Technology (IN)
Publication Details
- Published
- 2025-03-07
- DOI
- https://doi.org/10.1109/icdt63985.2025.10986366
- Citations
- 1
- Primary Topic
- Online Learning and Analytics
- Type
- article
- Field-Weighted Citation Impact
- 1.69