Digital twins for the ripening of plant products and sustainable packaging
The aim of the project is to develop a digital twin to optimize the packaging and shelf life of plant-based products. Advanced machine learning algorithms will be used to analyze the interaction between antimicrobial, cycle-oriented packaging solutions and the ripening process of the products.Further information can be found here.
Process mapping through machine learning
The goal of the project is to create a digital process map using machine learning. The focus is on the analysis of food processes for the prediction of critical states with respect to process and quality parameters. Critical states will be predicted using a fermented and shelf stable food product as an example. Further information can be found here.
Integrated Hybrid Optimization of Autonomous Self-adaptive Systems
This project aims to develop a hybrid Self-Adaptive and Self-Organizing (SASO) system that combines system-wide central planning with fully autonomous adaptation decisions of the local entities. The central control unit will thereby be equipped and supported by an optimizer framework. More information can be found here.
AI & Data Science Certificate Hohenheim (AIDAHO)
This project aims to establish an interdisciplinary, study-accompanying qualification program to promote the AI competencies of students from all three Hohenheim faculties - Agricultural Sciences, Natural Sciences, and Economic and Social Sciences. The Department of Food Informatics participates in this BMBF founded project mainly with the conception and initialization of a learning platform for automated assessment of students' programming submissions. Further information can be found here.
The intelligent, digitized Food Supply Chain (2022-2023)
This project focuses on the development of the smart food supply chain. Novel sensors support the data collection. Current trends in machine learning on the edge (EdgeML), i.e. data analysis directly at the point of origin, enable real-time analysis and predictive detection of critical conditions. The primary objective is to study the integration of different technologies in the food supply chain: smart sensors for data generation, blockchain technology for data storage and traceability, and EdgeML technology for real-time food analytics. Further information are available here.