Dish4u : a crowdsourcing app for food taste mining
Määttä, Tuomas; Holmi, Eetu (2024-09-23)
Määttä, Tuomas
Holmi, Eetu
T. Määttä; E. Holmi
23.09.2024
© 2024 Tuomas Määttä, Eetu Holmi. Ellei toisin mainita, uudelleenkäyttö on sallittu Creative Commons Attribution 4.0 International (CC-BY 4.0) -lisenssillä (https://creativecommons.org/licenses/by/4.0/). Uudelleenkäyttö on sallittua edellyttäen, että lähde mainitaan asianmukaisesti ja mahdolliset muutokset merkitään. Sellaisten osien käyttö tai jäljentäminen, jotka eivät ole tekijän tai tekijöiden omaisuutta, saattaa edellyttää lupaa suoraan asianomaisilta oikeudenhaltijoilta.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202409236028
https://urn.fi/URN:NBN:fi:oulu-202409236028
Tiivistelmä
This thesis addresses the development and evaluation of a cross-platform mobile application designed to assist users in managing their physical health through dietary decisions based on nutritional data. The application was developed using Flutter, an open-source framework, allowing the application deployment across multiple platforms including Android, iOS, and web browsers from a single codebase. Firebase was used for back-end services, providing real-time data synchronization, user authentication, and data storage.
The open Fineli nutritional data was used to create the main database. The Fineli data is maintained by the Finnish Institute for Health and Welfare and was used to calculate Nutri-Scores and display detailed nutritional information about dishes to the users. The Fineli database provided a solid foundation with its accurate and comprehensive nutritional values, but significant challenges were encountered due to a lack of data for specific dishes and portion sizes. These limitations show the need for more precise and comprehensive data from restaurants and Fineli to make the data better suited to help create restaurant focused dietary recommendation applications for the Finnish population.
Performance testing showed that the application met its functional and performance requirements, with sufficient results in load time, responsiveness, and data retrieval across different platforms. User feedback was positive, with the best feedback being the ease of use of the application. However, there were areas to improve particularly the user interface for smaller devices, enhancing the recommendation system, and improving data accuracy.
The thesis ends with suggestions for future work, including the integration of more advanced recommendation algorithms, larger datasets, and the use of artificial intelligence to improve the capabilities of the application. These improvements could include the use of large language models for personalized recommendations and visual-aware food recognition to refine the user experience.
The open Fineli nutritional data was used to create the main database. The Fineli data is maintained by the Finnish Institute for Health and Welfare and was used to calculate Nutri-Scores and display detailed nutritional information about dishes to the users. The Fineli database provided a solid foundation with its accurate and comprehensive nutritional values, but significant challenges were encountered due to a lack of data for specific dishes and portion sizes. These limitations show the need for more precise and comprehensive data from restaurants and Fineli to make the data better suited to help create restaurant focused dietary recommendation applications for the Finnish population.
Performance testing showed that the application met its functional and performance requirements, with sufficient results in load time, responsiveness, and data retrieval across different platforms. User feedback was positive, with the best feedback being the ease of use of the application. However, there were areas to improve particularly the user interface for smaller devices, enhancing the recommendation system, and improving data accuracy.
The thesis ends with suggestions for future work, including the integration of more advanced recommendation algorithms, larger datasets, and the use of artificial intelligence to improve the capabilities of the application. These improvements could include the use of large language models for personalized recommendations and visual-aware food recognition to refine the user experience.
Kokoelmat
- Avoin saatavuus [38841]