About the section
The section was established on 1st of January 2020 out of a working group of the former unit Embodied Systems for Robotics and Learning at the Mærsk Mc-Kinney Møller Institute. Located at the Mærsk building at the Odense campus of SDU, the section hosts the creative space for exciting research.
Our backgrounds span from pure science (including mathematics and physics) to applied disciplines (such as biostatistics, epidemiology, computer science, and engineering). This gives us a broad perspective to research new, innovative solutions in a variety of fields.
Our focus lies on the application of artificial intelligence and data science to advance research and provide data-driven solutions within the medical and energy sectors. Due to our long presence at SDU, we have established over the years strong collaborations with clinical researchers and companies, both in Denmark and abroad. Together with our collaborators, we are improving the way of handling and gaining insight from data, therefore creating knowledge and value for the society.
Organisation
The section is led by Esmaeil S. Nadimi with administrative support by Sussie Iuel‑Brockdorff.
AI in health
In most medical settings, an extensive amount of patient data is generated and recorded every day. These data often contain useful information that can be used to improve current medical procedures and treatment options. However, processing this enormous amount of heterogenous and complex data is not a simple task.
AI techniques rise as a solution to effectively use and integrate these different types of data to advance the healthcare sector towards e.g.: improved diagnostic tools, efficient prognosis of clinical outcomes, and highly personalized treatment options, taking into account the entire medical journey of each patient. Applying appropriate AI tools, together with the use of well-suited data, can thus reduce the amount of unnecessary testing and invasive treatment, which often introduce side effects and produce no diagnostic or health value to patient. Besides, this allows for a better resource allocation within the healthcare section, therefore increasing treatment for those in need.
AI and Big data analytics in clean energy
Along with the growing energy demand of modern society, generating affordable and clean energy becomes imperative. Wind and fusion energy are suitable candidates to cover future demand. But to fully substitute existing energy plants, we need to improve reliability and availability. AI, statistical machine learning, and data science span the foundation for accelerating research in clean energy. The challenges faced in this field range from Big-data analytics to physical modelling.
Within wind energy, we are focusing on monitoring the behavior of wind turbines under normal and abnormal conditions and operational states. Further, our research is providing a platform for performance benchmarks, targeting the manufactures and their customers, providing a predictive framework to facilitate remaining lifetime estimations and optimal operation and maintenance plans.
In contrast, fusion energy is still in an exploratory phase, where possible reactor types and their setup are researched. Extensive computer simulations are the tool of choice in this phase, due to the high costs and long durations of physically building such a reactor. Using AI and especially physics informed networks, we research faster simulation codes to converge swifter towards the fusion reactor of the future.