Field of research
The Analytics and AI group take a multidisciplinary approach to finding the best AI solutions for the industry and the public sector.
Our three main research areas, partially overlapping, are:
- Knowledge-informed AI: Models that combine domain knowledge and data-driven methods. The domain knowledge may be based on the experience and understanding of experts and operators, or it may be mathematical models based on the underlying physics of the system.
- Machine learning and optimization: Machine learning can be used to continuously improve optimization algorithms from data, particularly when modelling systems that change over time. This includes system control with reinforcement learning.
- Time series learning: Mainly on physical systems with sensor data, with applications in predictive maintenance, condition monitoring and anomaly detection.
The Analytics and AI group comprises researchers with diverse backgrounds in physics, mathematics, statistics, cybernetics and informatics. Based on this, we have built up expertise within AI for physical processes and industrial systems. The applications cover a wide range of domains such as process industry, logistics, construction, energy and many others.
Together with our partners, we take time to understand the problem we want to solve with AI rather than going straight to working with the data. We believe that the best AI solutions for complicated physical systems can only be found through a fundamental understanding of what the data represents. We stay updated on the latest advancements in AI, while conducting basic research and developing machine learning methods tailored to the specific challenges of our partners.