FitIQ: A Comprehensive Survey on AI-Based Personalized Fitness Recommendation Systems Using Health and Lifestyle Data

Author

Aditi M, Varsha S Marashetty, Mamatha M, Rakshitha M, and Dr. Nirmala H


Abstract

 The increasing prevalence of sedentary lifestyles, unhealthy dietary habits, inadequate sleep, and stress has created a growing need for intelligent and personalized fitness guidance. Existing fitness and health systems have demonstrated the effectiveness of machine learning, IoT-based monitoring, and explainable artificial intelligence for activity recognition, health prediction, and personalized recommendations; however, limitations such as static recommendations, limited behavioural tracking, dependence on wearable devices, lack of explainability, and insufficient representation of Indian users remain evident in the reviewed literature. FitIQ will be developed as an AI-based personalized fitness recommendation framework that will integrate biometric, behavioural, lifestyle, and dietary information to provide individualized fitness guidance. The framework will consider parameters such as physical activity, sleep, stress, nutrition, and fitness-related characteristics to support personalized analysis and recommendations. Machine learning techniques will be used for health and fitness analysis, while explainable AI, particularly SHAP-based analysis, will be incorporated to improve the transparency and interpretability of generated recommendations. The framework will further emphasize adaptive and continuous analysis rather than relying solely on static user information, with the objective of supporting personalized exercise, dietary, and wellness recommendations. The Phase-I work will establish the conceptual framework, system architecture, and research foundation required for the subsequent implementation and evaluation of FitIQ.


Keywords

Artificial Intelligence, Machine Learning, Personalized Fitness Recommendation, Explainable Artificial Intelligence, Health Analytics, Lifestyle Monitoring, Obesity Prediction, Sleep Analysis, Stress Analysis.



Full Text:

Download Paper PDF


References


  1. Venkata Krishna, V. Saritha, and P. Jayasri, “BRPHM: Blockchain-Enabled Real-Time Personalized Health and Nutrition Management Framework Using IoT and AI,” Frontiers in Blockchain, vol. 9, p. 1765645, Jan. 2026.
  2. Adhikari et al., “Healthcare Utilization and Chronic Condition Clusters in Multimorbidity Patients Using Weighted K-Means: A Register-Based Study in Denmark,” BMC Health Services Research, 2026.
  3. Jamloki, C. Garcia, H. Kaneko, and S. Inoue, “Explainable AI for Clinical Data from EHR Using SHAP and LLMBased Knowledge,” in Proc. UCAmI 2025, Lecture Notes in Networks and Systems, vol. 1819, Springer, Cham, 2026.
  4. Wang et al., “On Cost-Effectiveness of Language Models for Time Series Anomaly Detection,” MDPI Information, vol. 17, no. 1, p. 72, Jan. 2026.
  5. Jubair and M. Mehenaz, “Utilizing Machine Learning Algorithms for Personalized Workout Recommendations and Monitoring: A Systematic Review,” Digital Health, vol. 11, SAGE Publications, Sep. 2025.
  6. Wang, S. Zhao et al., “Sleep Quality and Stress as Influences on College Students Physical Activity Participation,” Frontiers in Public Health, vol. 13, p. 1640974, Oct. 2025.
  7. Li et al., “Effects of Different Physical Activity Interventions on Women's Sleep: A Systematic Review and Network Meta-Analysis,” Frontiers in Psychology, vol. 16, p. 1704980, Nov. 2025.
  8. Zhang, Y. Lou et al., “Random Forest-Based Identification and Ranking of Predictive Factors for Physical Activity,” Frontiers in Public Health, vol. 13, p. 1699606, Nov. 2025.
  9. Naveed et al., “IoT Based Health Monitoring with Diet, Exercise and Calories Recommendation Using Machine Learning,” Human-Centric Intelligent Systems, Springer, Apr. 2025.
  10. Gormez et al., “Prediction of Obesity Levels Based on Physical Activity and Eating Habits with ML and XAI,” Frontiers in Physiology, vol. 16, p. 1549306, 2025.
  11. T. Lee et al., “Evaluating Algorithmic Fairness of ML Models in Predicting Underweight, Overweight, and Adiposity,” PLOS Digital Health, vol. 4, no. 11, p. e0000951, Nov. 2025.
  12. Woll et al., “Personalized Fitness Recommendations Using Machine Learning for Optimized National Health Strategy,” Scientific Reports, Nature, vol. 15, p. 41652, Nov. 2025.
  13. Jamal et al., “Explainable Artificial Intelligence in Clinical Decision Support Systems,” MDPI Applied Sciences, Sep. 2025.
  14. C. Genc and E. Arican, “Obesity Classification: A Comparative Study of ML Models,” Revista da Associacao Medica Brasileira, vol. 71, no. 1, p. e20241282, Mar. 2025.
  15. Li et al., “Effects of Different Physical Activity Interventions on Women's Sleep,” Frontiers in Psychology, vol. 16, 2025.
  16. H. Kozan Cikirikci and M. N. Esin, “The Impact of Machine Learning on Physical Activity-Related Health Outcomes,” International Nursing Review, vol. 72, 2025.
  17. Rajesh et al., “A Novel Hybrid Approach to Enhancing Obesity Prediction Using Ensemble Machine Learning,” European Physical Journal Special Topics, Springer, Apr. 2025.
  18. Wood et al., “Predicting Obesity Trends Using Machine Learning from Big Data Analytics Approach,” in Proc. IEEE International Conference on Computing and Communication, IEEE, 2024.
  19. P. Kaur, M. Orstad et al., “The Relationship Between Sleep Quantity, Sleep Quality, and Weight Loss in Adults,” Clinical Obesity, vol. 14, no. 2, p. e12634, 2024.
  20. Lai et al., “Deep Learning for Time Series Anomaly Detection: A Survey,” ACM Computing Surveys, vol. 57, no. 1, 2024.

 

 

Share your valuable work from Social Media Buttons