NUTRI AI Prediction of Calorie Intake and Nutrient Deficiency using Machine Learning on Dietary Data

Yamuna T R and R Gnanaselvam

International Journal of Scientific Research in Science and Technology, 2025, vol. 12, issue 4, 91-97

Abstract: In today’s fast-paced world, the importance of maintaining a balanced diet and understanding individual nutritional needs has become increasingly significant, as modern lifestyles contribute to an array of health challenges, including nutrient deficiencies and diet-related diseases. Despite a widespread awareness of the benefits of nutrition, many people still lack the tools and guidance to make informed dietary decisions tailored to their unique health goals, lifestyle, and dietary preferences. NutrIAI, a personalized nutritional recommendation system, aims to bridge this gap by offering science- backed dietary guidance that empowers users to optimize their nutritional intake and align it with their health objectives. NutrIAI leverages artificial intelligence, machine learning, and data science techniques to provide customized dietary recommendations based on individual user profiles. The core of NutrIAI is a powerful data-driven model trained on extensive datasets, such as the What We Eat in America (WWEIA) dataset from the National Health and Nutrition Examination Survey (NHANES). This dataset offers a comprehensive view of typical dietary patterns, food composition, and nutrient intake, allowing NutrIAI to deliver precise nutritional insights. The system is designed to assess users’ nutritional intake, identify potential deficiencies, and suggest specific foods that fulfill these needs, catering to a range of dietary and health preferences. The project is structured around three phases to ensure functionality, usability, and scalability. In Phase 1, the system was developed to provide continuous enhancements and user feedback integration, ensuring that NutrIAI adapts to user needs effectively. Aligned with the United Nations’ Sustainable Development Goal 3: "Ensure healthy lives and promote well-being for all at all ages," NutrIAI not only contributes to public health by promoting balanced nutrition but also addresses broader social concerns by foundational dietary recommendations, covering key aspects such as calorie estimation, nutrient breakdown, and basic dietary advice. The core functionality was augmented in Phase 2 to address specific health concerns, such as providing tailored recommendations for users with chronic conditions, like diabetes or hypertension, where specific nutrient management is critical. This phase also introduced a personalized approach to mitigate nutrient deficiencies by suggesting foods that are rich in vitamins, minerals, and other essential nutrients. Phase 3 enhanced the user experience by incorporating an image classification feature that allows users to identify foods through images, providing instant nutrient information and calorie estimates for a more interactive experience. The architecture of NutrIAI combines various modules to ensure accuracy, responsiveness, and a seamless user experience. At its core is a recommendation engine that analyzes individual user data, including age, gender, health conditions, and specific dietary goals, to tailor suggestions accordingly. This engine is supported by a user-friendly interface, enabling users to interact with the system effortlessly. Additionally, NutrIAI incorporates a flexible, scalable backend capable of handling extensive data processing and real-time model predictions, ensuring that users receive timely recommendations. To evaluate and refine its recommendations, NutrIAI includes comprehensive testing and validation stages. A/B testing and functional test cases are applied to validate user interaction scenarios, while model accuracy is constantly monitored to maintain high-performance standards. The agile methodology followed in the project development, with structured sprints and iterative improvements, has allowed for fostering better eating habits that can prevent and manage chronic diseases. The project’s long-term vision includes expanding its functionality to support wearable health data integration, offering real-time insights, and developing a mobile application version for broader accessibility..

Keywords: CNN; WSN; RFID (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrst.com/home/article/view/IJSRST251258 Abstract page (text/html)
https://ijsrst.com/home/article/download/IJSRST251258/IJSRST251258 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:etm:ijsrst:v12:y2025:i4:id:984

DOI: 10.32628/IJSRST251258

Access Statistics for this article

More articles in International Journal of Scientific Research in Science and Technology from Technoscience Academy
Bibliographic data for series maintained by Pankaj Sharma ().