AyurDiet OS: An Intelligent Hybrid Ayurvedic Nutritional Diet Planning and Recommendation System

Abstract

AyurDiet OS is an online diet planning platform that assists in designing a tailored diet one by one, based on Ayurveda and the contemporary nutritional science to inform people on their biological requirements. The majority of diet applications follow only one line of action which is to track calories and count the macronutrients in order to direct diet, however, this does not consider how an individual would respond based on his/her constitution (i.e. body type), his/her digestive capability of certain types of food and how the seasons might influence how we metabolize food in accordance with principles discussed in Ayurveda. In this Platform, an Ayur-Nutri Hybrid Score (ANH-Score) algorithm is suggested, which calculates the compatibility of food products based on the Ayurvedic principles and their nutritional properties. This Platform includes five modules: Prakriti assessment, Food scoring, Meal composition, Detection of food item incompatibility ( according to the principles of Viruddha Aahara) and an AI-based diet consultant. The trial analysis demonstrates that the system is able to make balanced meal plans and identify the food combinations that do not have to be taken simultaneously and provide patients and health specialists with instant nutrition information.

Introduction

This paper presents AyurDiet OS, a hybrid diet recommendation system that combines Ayurvedic dietary principles with modern nutritional science to provide personalized dietary guidance. Unlike conventional diet applications that mainly focus on calories and nutrients, AyurDiet OS considers an individual's Prakriti (body constitution), Agni (digestive capacity), seasonal influences, and Ayurvedic food properties such as Rasa (taste), Virya (thermal potency), and Vipaka (post-digestive effect).

The literature review highlights existing research on Ayurvedic diet recommendation systems, machine learning-based Prakriti classification, fuzzy logic approaches, and AI-powered nutrition applications. However, most previous systems either focus only on Ayurvedic constitution or only on food recommendations, with limited integration of Ayurveda and modern nutritional evaluation.

To address this gap, AyurDiet OS introduces a computational framework that assesses a user's Prakriti through a questionnaire and calculates dosha distributions (Vata, Pitta, and Kapha). Foods are annotated with both Ayurvedic and nutritional attributes, including taste, thermal effect, dosha influence, calories, protein, carbohydrates, fats, fiber, and micronutrients.

A key innovation is the Ayur-Nutri Hybrid Score (ANH-Score), which combines Ayurvedic compatibility and nutritional quality to evaluate food suitability. The system also employs a meal composition algorithm that generates personalized meal plans while satisfying constraints such as calorie limits, protein requirements, taste diversity, and food compatibility. Additionally, it incorporates Viruddha Aahara (food incompatibility) detection using a graph-based model to identify harmful food combinations and reject unsuitable meal plans.

The architecture follows a modular client-server design consisting of a user interface, API layer, algorithm layer, knowledge-processing layer, and food database. The system integrates Ayurvedic knowledge with nutritional science through scalable computational models and supports future enhancements using artificial intelligence and machine learning.

Conclusion

AyurDietOS combines Ayurveda with modern nutrition and allows individuals to create personalized diets using the Ayur-Nutri Hybrid (ANH-Score). This paper outlines how the two systems work together by adding nutritional values (or metrics) to the Ayurvedic compatibility values to create an overall compatibility assessment score. Therefore, an individual\'s Prakriti (hereditary constitution) is assessed and the properties of foods are annotated. The system uses the principles of Viruddha-Aahara (Incompatible Foods) to detect incompatible food combinations and construct a diet plan that is balanced, compatible, and ultimately reflects the individual\'s Prakriti. Therefore, this study shows that computer assistance in dietary planning can help to create a more intelligent and personalized diet plan for individuals. Future directions of the project include expanding the food and recipe database to include more food from regional and international sources, developing machine learning models that can learn from individual user profiles, integrating with current mobile and wearable devices for real-time dietary assessment and creating partnerships with Ayurvedic practitioners and conducting clinical trials to validate and assess the ANH-Score as a reliable and useful tool for healthcare.

References

[1] Heart Disease Diagnosis and Diet Recommendation System Using Ayurvedic Dosha Analysis, EAI Endorsed Transactions on Internet of Things, 2023. [2] Ismayilova, A., Liu, X., Zambrano, J. I., and Perez Gutierrez, L., Food Recommender: Deep Learning Approach for Predicting Daily Diet Based on Body Prakriti, International Journal of Health Sciences, 2022. [3] Diet Recommendation Based on Prakriti and Season Using Fuzzy Ontology and Type-2 Fuzzy Logic, IEEE International Conference on Computational Intelligence and Computing Research (ICCUBEA), 2016. [4] Das, S., Rathod, S., and Nandgaonkar, V., Smart Diet India: An AI-Powered Platform for Personalized and Culturally Adaptive Indian Diet Management, International Journal of Food and Nutritional Sciences. [5] Madaan, V., and Goyal, A., Predicting Ayurveda-Based Constituent Balancing in Human Body Using Machine Learning Methods, IEEE Access. [6] Veena and Verma, V., An Appraisal on Ayurvedic Diet and Dietary Intake Considerations in View of Nutrition Science, The Indian Journal of Nutrition and Dietetics, 2018. [7] Patwardhan, B., Mutalik, G., and Tillu, G., Integrative Approaches for Ayurvedic Nutrition and Personalized Medicine, Journal of Ethnopharmacology, 2006. [8] Trattner, C., and Elsweiler, D., Food Recommender Systems: Important Contributions, Challenges, and Future Research Directions, ACM Computing Surveys, 2017. [9] P. Amuthabala and R. Santhosh, “Robust analysis and optimization of a novel efficient quality assurance model in data warehousing,” in Proc. 34th Int. Conf. Radioelektronika, Košice, Slovakia. [10] R. Indhumathi, K. Amuthabala, G. Kiruthiga, N. Yuvaraj, and A. Pandey, “Design of task scheduling and fault tolerance mechanism based on GWO algorithm for attaining better QoS in cloud system,”.

Copyright

Copyright © 2026 Vidhi Dattatraya Kamat, Dr. K. Amuthabala , V. Srinath Reddy, T. Khatwangadar Reddy, V. Allwin Romario Fernando. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.