Level: MSc
Overview
Food fraud is a significant issue that threatens the safety and integrity of food products available on the market. Research has revealed that food fraud affects a wide range of products, with fraudulent activities ranging from intentional adulteration of food to falsification of documentation. Identifying vulnerabilities in the food supply chain and determining which products and fraud types require assessment are critical steps to safeguarding food quality and safety. This MSc project aims to use artificial intelligence to develop a data-driven approach for assessing food fraud vulnerability in the main food supply chains such as honey supply chain. The goal is to predict the level of vulnerability, potential food fraud types and adulterants at each stage of the supply chain.
Description
The project will involve collecting and analyzing data from various sources, including publicly available food fraud databases, literature, and surveys. The goal is to develop an AI model to predict the food fraud vulnerabilities in honey supply chain. This includes identifying fraud types such as adulteration, mislabeling, or counterfeiting and potential adulterants at each stage of the supply chain, from farm to fork. By analyzing vulnerabilities, the model aims to enhance food safety and transparency.
Objectives
- Conduct a comprehensive literature review on AI techniques, food fraud, food fraud databases and vulnerability assessment tools models.
- Identify, collect and preprocess relevant online food fraud databases, including literature and news articles and health-related websites.
- Explore different AI algorithms, including machine learning models for predicting food fraud.
Tasks
The work in this master thesis entails:
- Literature Review: Review existing research on food fraud vulnerability assessment using open access data and AI techniques, identifying key findings and research gaps.
- Data Collection and Preparation: Identify and preprocess relevant open access data for analysis.
- AI Model Development: Develop machine learning models to assess food fraud vulnerability using a data-driven approach.
- Results Reporting: Prepare a report summarizing methodology, results, and conclusions.
Literature
- Y. Bouzembrak, N. Liu, W. Mu, A. Gavai, L. Manning, F. Butler, H.J.P. Marvin (2024), Data driven food fraud vulnerability assessment using Bayesian Network: Spices supply chain, Food Control, Volume 164, 2024.
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
Keywords: Artificial Intelligence, food quality, food safety and health.
Contact person(s)
Yamine Bouzembrak (yamine.bouzembrak@wur.nl)
Erika Silletti (erika.silletti@wur.nl)