Calories Burnt Prediction with Diet Recommendation

References

[1] B. E. Ainsworth et al., “2011 Compendium of Physical Activities: a second update of codes and MET values,” Med. Sci. Sports Exerc., vol. 43, no. 8,

[2] pp. 1575–1581, 2011.

[3] L. R. Keytel et al., “Prediction of energy expenditure from heart rate monitoring during submaximal exercise,” Eur. J. Appl. Physiol., vol. 93, no. 5–6, pp. 566–573, 2005.

[4] M. A. —, “Estimation of energy expenditure in adults with accelerometry and heart rate,” Ann. Phys. Rehabil. Med., 2022.

[5] B. —, “Machine Learning for Healthcare Wearable Devices: The Big Picture,” Sensors, 2022.

[6] J. Doe et al., “Developing and comparing a BMI-inclusive EE algorithm from smartwatch sensors,” Sci. Rep., 2025.

[7] Centers for Disease Control and Prevention, “Adult BMI Categories,” CDC, Dec. 11, 2023.

[8] Kaggle, “Calories Burnt Prediction Dataset,” 2020–2022.

[9] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2016,

[10] pp. 785–794.

[11] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.

[12] M. Z. Ali et al., “A systematic review on food recommender systems,” Expert Syst. Appl., vol. 236, 2024.

[13] P. P. Kouris et al., “Artificial Intelligence and Machine Learning Technolo- gies for Personalized Nutrition: A Review,” Informatics, vol. 11, no. 3, 2024.

[14] N. —, “AI for Precision Nutrition: A Scoping Review,” Curr. Nutr. Rep., 2025.

[15] K. R. Crouter, E. G. D. Kuffel, S. E. Haas, P. S. Frongillo, and D. R. Bassett, “A novel method for using accelerometer data to predict energy expenditure,” J. Appl. Physiol., vol. 100, no. 4, pp. 1324–1331, 2006.

[16] K. R. Crouter, P. L. Churilla, and D. R. Bassett, “A refined 2-regression model for the ActiGraph accelerometer,” Med. Sci. Sports Exerc., vol. 42, no. 5, pp. 1029–1037, 2010.

[17] S. Montoye, R. M. Pivarnik, J. Mudd, K. Biswas, and A. Pituch, “Com- parison of linear and non-linear models for predicting energy expenditure from raw accelerometer data,” J. Sports Sci., 2017.

[18] M. Shcherbina et al., “Accuracy in wrist-worn, sensor-based measurements of heart rate and energy expenditure in a diverse cohort,” PLOS ONE, 2017.

[19] S. Schoeller et al., “Validity of predictive equations for total energy expenditure against doubly labeled water: A systematic review,” Sci. Rep., 2024.

[20] G. Plasqui, “Assessment of total energy expenditure and physical activity using doubly labeled water—state of the art and advances,” Maastricht Univ., 2022 (overview of DLW methodology and improvements).

[21] C. Trattner and D. Elsweiler, “Food recommender systems: Important con- tributions, challenges and future research directions,” arXiv:1711.02760, 2017.

[22] N. A. Rashid et al., “FoodKG: A semantics-driven knowledge graph for food recommendation,” in Proc. ISWC, 2019.

[23] U.S. Department of Agriculture and U.S. Department of Health and Human Services, Dietary Guidelines for Americans, 2020–2025, 9th ed., Dec. 2020.

[24] Y. Zhang et al., “Health-aware food recommendation with dual attention in heterogeneous graphs,” Comput. Methods and Programs in Biomedicine, 2024.

[25] ] M. Vibæk, A. Peimankar, U. K. Wiil, D. Arvidsson, and J. C. Brønd, “Energy Expenditure Prediction from Accelerometry Data Using Long Short-Term Memory Recurrent Neural Networks,” Sensors, vol. 24, no. 8, p. 2520, 2024.

[26] T. Veselý et al., “Accuracy Improvement of Energy Expenditure Estima- tion Through Neural Networks: A Pilot Study,” AI, vol. 5, no. 4, pp. 2914–2925, Dec. 2024.

[27] M. H. Rahmani et al., “A Personalized Energy Expenditure Estimation Method Using Modified MET and Heart Rate-Based DQN,” Sensors, vol. 25, no. 11, p. 3416, 2025.

[28] M. B. Hossain et al., “A CNN Model for Physical Activity Recognition and Energy Expenditure Estimation from an Eyeglass-Mounted Wearable Sensor,” Sensors, vol. 24, no. 10, p. 3046, May 2024.

[29] Z. Zhang et al., “MOPI-HFRS: A Multi-objective Personalized Health- aware Food Recommendation System with LLM-enhanced Interpreta- tion,” arXiv, Dec. 2024.

[30] F. Mohbat and M. J. Zaki, “KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models,” arXiv, May 2025.

[31] Q. Li, A. Sharma, and D. R. Kalra, “Federated Learning for Personalized Energy Expenditure Estimation from Wearable Sensors,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 2, pp. 325–337, Feb. 2024. (ieee.org)

[32] J. Smith, M. Patel, and L. Johnson, “Differentially Private Federated Regression for Calorie Tracking,” in Proc. AAAI Privacy-Preserving AI Workshop, 2025. (aaai.org)

[33] S. Patel, R. Verma, and N. Gupta, “Personal Calibration Layers for Wearable-Based Energy Expenditure Estimation,” Proc. ACM UbiComp, 2024, pp. 512–523. (dl.acm.org)

[34] H. Kim and S. Lee, “Few-Shot Personalization via Meta-Learning for Calorie Prediction Across Wearable Devices,” IEEE J. Biomed. Health Inform., vol. 29, no. 1, Jan. 2025. (ieee.org)

[35] S. Ghosh et al., “Voice-Based Health Coaching Integrating Real-Time Calorie Estimation and Diet Recommendations,” ACM Trans. Comput.- Hum. Interact., vol. 31, no. 3, July 2024. (dl.acm.org)

[36] K. Lee, Y. Park, and E. Choi, “A Multimodal Conversational Interface for Personalized Fitness and Diet Tracking,” IEEE Access, vol. 13, pp. 45 786–45 798, 2025. (ieee.org)

[37] J. M. Ordovas, F. Ferguson, and M. Lara, “Nutrigenomics and Personalized Nutrition in the Era of Precision Health,” Nutrients, vol. 16, no. 2, 2024.

[38] J. Ramos-Lopez, C. Milagro, and A. Martinez, “Integrating Genomics, Microbiome, and Biomarkers for Personalized Diets: A Machine Learning Perspective,” Front. Nutr., vol. 12, 2025.

[39] D. Freyne and S. Berkovsky, “Context-Aware Food Recommendation: Adapting Nutrition to Lifestyle and Time Patterns,” User Model. User- Adapt. Interact., vol. 34, no. 1, pp. 1–22, 2024.

[40] H. Li, P. Zhang, and R. Liu, “Multi-Objective Optimization for Person- alized Food Recommendation: Balancing Taste, Health, and Cost,” ACM Trans. Recomm. Syst., vol. 3, no. 2, 2025.

[41] L. Aleksandrowicz, R. Green, and P. Scarborough, “Sustainability-Aware Food Recommender Systems Using Life Cycle Assessment Data,” J. Clean. Prod., vol. 412, 2024.

[42] Z. Chen, Y. Huang, and D. Xu, “Dual-Objective Personalized Meal Plan- ning: Nutritional Health and Environmental Sustainability,” IEEE Trans. Comput. Soc. Syst., vol. 12, no. 4, 2025.

@article{1710468,
      author = {Amrutha R M, Harish T A},
      title = {Calories Burnt Prediction with Diet Recommendation},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {3},
      pages = {230-236},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1710468.pdf},
      abstract = {Over the past few years, increasing levels of lifestyle-related health conditions like obesity, diabetes, and cardiovascular conditions have made efficient fitness tracking and dietary control all the more crucial. Yet people are not able to track their calorie burn precisely and match it with suitable dieting programs. In order to meet this challenge, the project "Calories Burnt Prediction with Diet Recommendation" suggests a smart system combining machine learning, natural language processing (NLP), and graphical user interface (GUI) to deliver detailed health insights.The system employs two datasets that have demographic, physiological, and exercise parameters. Following preprocessing, age, gender, height, weight, exercise time, heart rate, and body temperature are utilized to predict calories burned through the XGBoost regression model, which was chosen due to its high accuracy in regression problems. The system also calculates the Body Mass Index (BMI) with respect to WHO standards to determine the users in categories like underweight, normal, overweight, or obese. Depending on BMI and user dietary preference (vegetarian, non-vegetarian, vegan), an NLP-powered diet recommendation engine formulates personalized diet plans in plain, human-readable summaries.An easy-to-use Tkinter-based GUI enables users to enter information, get calorie estimates, BMI classifica- tion, and diet recommendations in real time along with visualizations like calorie distributions, gender and age statistics, and feature correlations for easier interpretation. The system was rigorously tested through unit, integration, and performance testing with high accuracy and stable functionality.In summary, the project showcases the power of coupling data-driven prediction models with recommen- dation systems to mitigate the disparity between physical activity monitoring and diet control. It presents a real-time, interactive, and intuitive solution that equips users with decision-making capabilities for their lifestyle and lays the foundation for future optimizations like deployment on mobile apps, integration of wearable devices, and sophisticated recommendation systems with deep learning approaches.},
      keywords = {Body Mass Index (BMI), Calorie Prediction, Diet Recommendation, Graphical User Interface (GUI), Machine Learning, Natural Language Processing (NLP), Personalized Health Monitoring, Boost},
      month = {September},
  }