Preprint / Version 1

The Ai Food App

##article.authors##

  • Arvind Krishna Sivakumar Polygence
  • Garrett Thomas

DOI:

https://doi.org/10.58445/rars.2089

Abstract

Creating recipes is a difficult task for people because sometimes there are only a few options in the fridge and people don't know recipes that can be made for that list. The AI-based food machine learning model presented in this work creates recipes according to user-specified parameters, including total calories, ingredients, cuisine, and dietary restrictions. The model creates recipes based on user preferences using ChatGPT. Using a Raspberry Pi, the application is developed in both device and online formats. This approach seeks to help users locate appropriate recipes that support different cuisines and their nutritional objectives for weight loss. In comparison to current neural network models devoted to recipe development, the method provides greater flexibility and adaptability. For example other models won't be able to deal with spelling mistakes and our model has a 94% success rate.

References

Jing Han, Xinyang Zhang, and Jingbo Shang. (2019). "Neural Recipe Generation with Ingredient-Pair Embedding." Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing.

Introducing chatgpt - openai. (n.d.). https://openai.com/index/chatgpt

to https://platform.openai.com/docs/assistants/overview and https://fdc.nal.usda.gov/

U.S. Department of Agriculture, Agricultural Research Service, Beltsville Human Nutrition Research Center. FoodData Central. [Internet]. Available from https://fdc.nal.usda.gov/.

Kusner, M. J., Paige, B., & Hernández-Lobato, J. M. (2017). "GRAM: Graph-based Attention Model for Recipe Generation." Proceedings of the 34th International Conference on Machine Learning (ICML).

Majumder, B. P., Menezes, R., Ghosh, S., & Shah, C. (2019). "Generating Recipes from Ingredients with Variational Autoencoders." Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

Trattner, C., & Elsweiler, D. (2019). "Food Recommender Systems: Important Contributions, Challenges, and Future Research Directions." arXiv preprint arXiv:1912.05165.

Downloads

Posted

2025-01-06