Next-Gen Fitness: AI-Based Diet Plans and Real-Time Exercise Monitoring with Gradient Boosting, GMM and MediaPipe
Article Sidebar
Main Article Content
Abstract
Global shifts toward sedentary habits and refined dietary choices are magnifying public-health pressures from obesity, metabolic dysregulation, and cardiovascular disease, positioning targeted, personalized fitness coaching tools at the forefront of preventive-care strategy. By embedding tailored nutritional and physical-activity plans into daily life, these tools reinforce adherence, enhance intrinsic motivation, and catalyze sustained wellness achievements—each moderated by real-time analytics, feedback loops, and progressive adaptation to evolving behavior and physiology. Their leading benefits include prolonged engagement, diminished risk of relapse, and deep integration of healthful routines, culminating in lowered lifetime healthcare costs and improved individual life satisfaction. Current machine-learning approaches deliver commendable dietary and activity personalization yet often fragment the upstream clustering, forward-looking forecasting, and downstream monitoring into separate silos. This manuscript proposes a comprehensive intelligent coaching architecture that combines probabilistic Gaussian Mixture Models to cluster users by real-time activity and baseline health profile, fulfills dietary and regimen prescription by context-sensitive Extreme Gradient Boosted Trees, and pairs MediaPipe biosignal capture for on the-spot performance diagnosis and postural adjustment. User-background information—age, weight, and unique preferences—pours into the platform and sparks tailored exercise plans that refresh automatically via the linked mobile app, ensuring routines stay fresh and relevant. Progress is recorded continuously, and instant feedback is given to maintain safety during workouts. When tested against varied datasets, the system delivers strong results: Gaussian Mixture Model clustering reaches 92% in segmenting users, XGBoost-based recommendations report 95% precision, 93% recall, and 94% F1-score for personalizing plans, and posture tracking powered by MediaPipe achieves 96% accuracy with minimal latency. Collectively, the metrics confirm the platform’s effectiveness in fostering sustained and meaningful wellness engagement.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All articles published in JIWE are licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) License. Readers are allowed to
- Share — copy and redistribute the material in any medium or format under the following conditions:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use;
- NonCommercial — You may not use the material for commercial purposes;
- NoDerivatives — If you remix, transform, or build upon the material, you may not distribute the modified material.
References
[1] J. Lopez-Barreiro, J. L. Garcia-Soidan, L. Alvarez-Sabucedo, and J. M. Santos-Gago, "Machine learning-powered recommender systems for promoting healthy habits and active aging: A systematic review," Applied Sciences, vol. 14, no. 22, p. 10220, Nov. 2024, doi: 10.3390/app142210220.
[2] D. Tsolakidis, L. P. Gymnopoulos, and K. Dimitropoulos, "Artificial intelligence and machine learning technologies for personalized nutrition: A review," Informatics, vol. 11, no. 3, p. 62, Aug. 2024, doi: 10.3390/informatics11030062.
[3] S. Nagati, "Diet recommendation systems using machine learning: Approaches, challenges, and future directions," IRJET, vol. 6, no. 11, pp. 1872-1876, Nov. 2024, doi: 10.70127/irjedt.vol.6.issue12.1876.
[4] K. Samy, A. Osheba, H. S. El-Din, R. M. Sallam, and M. A. Elaziz, "Personalized nutrition recommendations using machine learning," in Proc. 2024 Int. Conf. Smart-Digital-Green Technologies and Artificial Intelligence Sciences (CSDGAIS), Suez, Egypt: IEEE, Dec. 2024, pp. 1-5, doi: 10.1109/CSDGAIS64098.2024.11064829.
[5] S. Hemaraju, P. M. Kaloor, and K. Arasu, "Yourcare: A diet and fitness recommendation system using machine learning algorithms," Guntur, India, 2023, p. 020011, doi: 10.1063/5.0134382.
[6] S. Mahadik, F. Antara, P. Chopra, A. Renuka, and O. Goel, "User-centric design in product development," Universal Research Reports, vol. 10, no. 4, pp. 473-492, Oct. 2023, doi: 10.36676/urr.v10.i4.1359.
[7] J. Lu, "Optimizing e-commerce with multi-objective recommendations using ensemble learning," in Proc. 2024 4th Int. Conf. Computer Systems (ICCS), Hangzhou, China: IEEE, Sep. 2024, pp. 167-171, doi: 10.1109/ICCS62594.2024.10795824.
[8] Q. Chen and S. Lee, "A machine learning approach to predict customer usage of a home workout platform," Applied Sciences, vol. 11, no. 21, p. 9927, Oct. 2021, doi: 10.3390/app11219927.
[9] F. Widyawati, A. Y. Dawod, and H. A. Santoso, "K-means clustering optimization of toddler malnutrition status using elbow method," Journal of Informatics and Web Engineering, vol. 4, no. 2, pp. 360-374, Jun. 2025, doi: 10.33093/jiwe.2025.4.2.23.
[10] J. Hong and H. Chun, "A prediction model for healthcare time-series data with a mixture of deep mixed effect models using Gaussian processes," Biomedical Signal Processing and Control, vol. 84, p. 104753, Jul. 2023, doi: 10.1016/j.bspc.2023.104753.
[11] M. C. P. Nilesh and B. Kalani, "Personal exercise assistant: Correcting exercise posture using modified OpenPose," MSEA, vol. 71, no. 4, pp. 10347-10358, Aug. 2022, doi: 10.17762/msea.v71i4.1871.
[12] T. P. T. Armand, O. Deji-Oloruntoba, S. Bhattacharjee, K. A. Nfor, and H.-C. Kim, "Optimizing longevity: Integrating smart nutrition and digital technologies for personalized anti-aging healthcare," in Proc. 2024 Int. Conf. Artificial Intelligence in Information and Communication (ICAIIC), Osaka, Japan: IEEE, Feb. 2024, pp. 243-248, doi: 10.1109/ICAIIC60209.2024.10463262.
[13] P. B. R., D. N. N. Kumari, B. Manikanta, A. P. Chandana, and Y. L. S. Aditya, "Personalized diet recommendation system using machine learning," SSRN Journal, 2024, doi: 10.2139/ssrn.4877349.
[14] C. Iwendi, S. Khan, J. H. Anajemba, A. K. Bashir, and F. Noor, "Realizing an efficient IoMT-assisted patient diet recommendation system through machine learning model," IEEE Access, vol. 8, pp. 28462-28474, 2020, doi: 10.1109/ACCESS.2020.2968537.
[15] R. Yera Toledo, A. A. Alzahrani, and L. Martinez, "A food recommender system considering nutritional information and user preferences," IEEE Access, vol. 7, pp. 96695-96711, 2019, doi: 10.1109/ACCESS.2019.2929413.
[16] J. Fang, V. C. Lee, H. Ji, and H. Wang, "Enhancing digital health services: A machine learning approach to personalized exercise goal setting," DIGITAL HEALTH, vol. 10, p. 20552076241233247, Sep. 2024, doi: 10.1177/20552076241233247.
[17] S. Forouzandeh, M. Rostami, K. Berahmand, and R. Sheikhpour, "Health-aware food recommendation system with dual attention in heterogeneous graphs," Computers in Biology and Medicine, vol. 169, p. 107882, Feb. 2024, doi: 10.1016/j.compbiomed.2023.107882.
[18] S. RahmathNisha, M. Aarthi, C. Shyamala, M. Pavithra, K. Vallipriyadharshini, and B. S. Raj, "Intelligent nutrition assistant application," in Proc. 2023 12th Int. Conf. Advanced Computing (ICoAC), Aug. 2023, pp. 1-6, doi: 10.1109/ICoAC59537.2023.10249611.
[19] W. Min, S. Jiang, and R. Jain, "Food recommendation: Framework, existing solutions, and challenges," IEEE Transactions on Multimedia, vol. 22, no. 10, pp. 2659-2671, Oct. 2020, doi: 10.1109/TMM.2019.2958761.
[20] G. Ispirova, T. Eftimov, S. Dzeroski, and B. K. Seljak, "MsGEN: Measuring generalization of nutrient value prediction across different recipe datasets," Expert Systems with Applications, vol. 237, p. 121507, Mar. 2024, doi: 10.1016/j.eswa.2023.121507.
[21] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA: ACM, Aug. 2016, pp. 785-794, doi: 10.1145/2939672.2939785.
[22] Z. B. Ter, P. Naveen, and J. Jayapradha, "Generative AI-based meal recommender system," Journal of Informatics and Web Engineering, vol. 4, no. 2, pp. 315-338, Jun. 2025, doi: 10.33093/jiwe.2025.4.2.20.