AI is the ability of a machine to display human-like capabilities such as reasoning, learning, planning and creativity. AI enables technical systems to perceive their environment, deal with what they perceive, solve problems and act to achieve a specific goal. The computer receives data - already prepared or gathered through its own sensors such as a camera - processes it and responds. AI systems are capable of adapting their behaviour to a certain degree by analysing the effects of previous actions and working autonomously. (What is artificial intelligence and how is it used? | News | European Parliament (europa.eu))
Various new and further developed technologies make it possible to produce very large amounts of data (e.g. image and video material, sequence data). The evaluation of such large amounts of data is a challenge for which AI methods can be used, especially the application of machine learning methods. Machine learning is a subarea of AI. It uses algorithms that learn from data and are thus able to recognise patterns and regularities.
Building and strenghtening AI and data competences:
As part of the German government's AI strategy, the AI and data competences in the research and advisory institutions of the Federal Ministry of Food and Agriculture (BMEL) are to be sustainably strengthened and developed. The institutions concerned have joined forces in the KIDA project (KI- und Daten-Akzelerator) and are intensifying their competence and resource development in order to realise the potential of data and methods of artificial intelligence in the fields of nutrition and agriculture. (Link: www.kida-bmel.de).
The main aim is to expand and network AI and data expertise, expand and operate AI and IT infrastructure, and make existing data usable for AI technologies and AI solutions.
The following questions are addressed in the KIDA working group:
- Automated real-time analysis of video recordings by using computer vision methods:
The goal of computer vision (CV) is to teach computers to see like humans. This includes the ability to recognise and track an object. Such methods are promising for automated monitoring of animal behaviour to identify indicators for the earliest possible detection of health problems and can be used to monitor animal welfare in general.
- Diagnostic metagenomic analyses:
For the analysis of sequence data sets (e.g. metagenome), pipelines for the identification of resistance genes are being used and developed. In particular, AI methods for the deduction of (new) inactivating enzymes (variants) for individual classes of antibiotics and synthesis pathways for antibiotics and metagenome data sets will be developed. (AG AMR, IfE)