Thesis subject
Artificial Intelligence to enhance the food enjoyment of individuals with smell disorders (MSc)
Smell disorders can greatly diminish the pleasure of eating, affecting both quality of life and nutrition. To address this issue, we aim to enhance the food enjoyment of individuals with smell disorders.
Short description
The ultimate goal of this project is to construct a comprehensive food (recipes) database enriched with taste and trigeminal profiles. This resource will prove invaluable in enhancing food enjoyment for individuals coping with smell loss. Our vision is to empower individuals with smell disorders by recommending the suitable food showing them detailed food taste profiles and providing sensory descriptions. By doing so, we hope to significantly enhance their food enjoyment and overall quality of life. By collecting data from surveys and taste trials using the existing Taste and Nevo database and applying advanced machine learning algorithms, we intend to decode the intricate food profiles, taking into account ingredients and cooking processes. This data will feed into AI models, allowing us to anticipate the taste profiles of various menus.
Objectives
- Conduct a literature review on AI techniques, and the sensory profile of food (e.g., taste, texture, etc)
- Preprocess the surveys data and the existing Taste and Nevo database.
- Explore different AI algorithms to predict the overall sensory profile of a food item (including taste, texture, and trigeminal sensations) based on its ingredients, cooking process, and other preparation methods,
Tasks
The work in this master thesis entails:
- Literature review: Conduct a review of existing research studies, to identify relevant studies on food taste using open access data and AI techniques. This will provide a foundation of knowledge and identify research gaps.
- Data collection and preparation: Identify relevant open access data sources and collect and preprocess the data.
- Combine the open-source data with the available collected data (i.e., Survey, taste trial, NEVO, SVT (taste database)
- AI models development: Use machine learning algorithms to develop a predictive model that can predict the overall sensory profile of a food item.
- Results reporting and documentation: Prepare a comprehensive report summarizing the research methodology, results, and conclusions.
Literature
- Machine learning prediction of the degree of food processing | Nature Communications
- The impact of perceptual interactions on perceived flavor – ScienceDirect
- Effect of Concentration on Taste-Taste Interactions in Foods for Elderly and Young Subjects (researchgate.net)
Requirements
- Courses: Programming in Python (INF-22306), Data Science Concepts (INF-34306) or Machine Learning (FTE-35306)
- Required skills/knowledge: Food and health, Machine Learning.
Key words: Artificial Intelligence, food taste, food enjoyment and health.
Contact person(s)
Yamine Bouzembrak (yamine.bouzembrak@wur.nl)
Parvaneh Parvin (parvaneh.parvin@wur.nl)