Home / Current Issue / Paper 1715935
FitCluster AI: A Semi-Personalized Fitness and Diet Recommendation System Using Rule-Based and Lightweight Machine Learning Techniques
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence
DOI: 10.64388/IREV9I10-1715935
Abstract
Maintaining a consistent fitness and dietary routine has become increasingly difficult in modern lifestyles due to lack of time, improper guidance, and absence of personalization. Many individuals rely on generic plans that fail to consider their unique body conditions and goals. This leads to ineffective results and lack of motivation. To address this issue, this paper presents FitCluster AI, a semi-personalized recommendation system that combines rule-based logic with lightweight machine learning techniques. The system utilizes user inputs such as age, height, weight, activity level, and fitness goals to categorize users into predefined clusters. Based on these clusters, rule-based logic is applied to generate tailored recommendations. Unlike deep learning approaches, the proposed system does not require large datasets or high computational resources, ensuring efficiency and privacy. Experimental results demonstrate that the system produces consistent and meaningful outputs across different user profiles. The proposed approach provides a practical solution for real-world fitness applications.
References
[1] World Health Organization, “Body Mass Index – BMI Classification,” WHO Guidelines. [Online]. Available: https://www.who.int
[2] Centers for Disease Control and Prevention, “About Adult BMI,” CDC Health Guidelines. [Online]. Available: https://www.cdc.gov
[3] American College of Sports Medicine, ACSM’s Guidelines for Exercise Testing and Prescription, 12th ed., Philadelphia: Lippincott Williams & Wilkins, 2024. [Online]. Available: https://www.acsm.org
[4] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016. [Online]. Available: https://www.deeplearningbook.org
[5] M. Grinberg, Flask Web Development: Developing Web Appli- cations with Python. O’Reilly Media, 2018. [Online]. Available: https://www.oreilly.com
[6] Official React Documentation, “React – A JavaScript Library for Build- ing User Interfaces.” [Online]. Available: https://react.dev
[7] FastAPI Documentation, “FastAPI Framework for Building APIs with Python.” [Online]. Available: https://fastapi.tiangolo.com
[8] PostgreSQL Global Development Group, “PostgreSQL Documentation: The world’s most advanced open-source relational database,” 2024. [Online]. Available: https://www.postgresql.org/docs
[9] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed., Pearson, 2021. [Online]. Available: https://www.pearson.com
[10] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning. Springer, 2009. [Online]. Available: https://link.springer.com
[11] Z. Waseem and D. Hovy, “Detecting offensive language in social media to protect adolescent online safety,” NAACL, 2016. [Online]. Available: https://arxiv.org/abs/1602.07350
[12] A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov, “Bag of tricks for efficient text classification,” EACL, 2017. [Online]. Available: https://arxiv.org/abs/1607.01759
[13] J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” 2019. [Online]. Available: https://arxiv.org/abs/1810.04805
[14] A. Vaswani et al., “Attention is all you need,” NeurIPS, 2017. [Online]. Available: https://arxiv.org/abs/1706.03762
[15] X. Zhao, L. Xia, and J. Tang, “Deep reinforcement learning for recom- mender systems: A survey and new perspectives,” arXiv, 2019. [Online]. Available: https://arxiv.org/abs/1901.01380
How to cite this paper
@article{1715935,
author = {B. Shashank, B. Chaitanya, K. Praveen, G. Shankar},
title = {FitCluster AI: A Semi-Personalized Fitness and Diet Recommendation System Using Rule-Based and Lightweight Machine Learning Techniques},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {94-100},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1715935.pdf},
abstract = {Maintaining a consistent fitness and dietary routine has become increasingly difficult in modern lifestyles due to lack of time, improper guidance, and absence of personalization. Many individuals rely on generic plans that fail to consider their unique body conditions and goals. This leads to ineffective results and lack of motivation. To address this issue, this paper presents FitCluster AI, a semi-personalized recommendation system that combines rule-based logic with lightweight machine learning techniques. The system utilizes user inputs such as age, height, weight, activity level, and fitness goals to categorize users into predefined clusters. Based on these clusters, rule-based logic is applied to generate tailored recommendations. Unlike deep learning approaches, the proposed system does not require large datasets or high computational resources, ensuring efficiency and privacy. Experimental results demonstrate that the system produces consistent and meaningful outputs across different user profiles. The proposed approach provides a practical solution for real-world fitness applications.},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1715935}
}