Big data voor de WOT vervolg food safety data infrastructuur (KB-37-002-006, KB-23-002-020, KB-15-006-028)

Project: LNV project

Project Details


The availability of large amounts of diverse food safety related data opens opportunities for linking different data types and extracting food safety knowledge. Using AI and Big data technologies, analytical data can be collected and processed more efficiently. In this project, we develop Big Data tools and AI algorithms to collect and process data from diffrent data sources which will give new knowledge from the data. These tools will be applied to solve practical food safety issues such automatic LC-hrMS data collection and processing, automatic systematic literature reviews, and prioritisation of chemical compounds.

The first task in this project will be the design and the implementation of a dashboard that links and integrate relevant open source databases to LC-hrMS results such as Wiki, RASFF, and PubMed. The dashboard will be implemented in the WFSR Big Data infrastructure as an application. In addition, a combination of AI models to automate the learning of peak detection in LC-hrMS data will be explored. 

In the second task, new ML algorithms will be developed to explore the possibility to classify scientific articles independent from the topic and to extract information automatically from the relevant articles (e.g. product name, hazard name, concentration, etc.). Furthermore, the KAP database will be integrated in the WFSR food safety Big data infrastructure with a user-friendly dashboard for the users.

The last activity is related to the development of a data collection and processing system of the parameters that are relevant for characterisation of the toxicity and occurrence of a compound. The developed system will be implemented in WFSR food safety big data infrastructure. In addition, a user-friendly dashboard will be developed where the user can get the required data automatically.

Effective start/end date1/01/1531/12/21


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.