The world of AI is developing rapidly with the advancement of technology, and applications of AI are becoming ubiquitous in almost all parts of academia and society. Our researchers are involved in a wide range of collaborations through which methods and techniques of AI are developed and applied. Here we show some examples of such projects.
Drones4Energy aims to build a collaborative, autonomous, and continuously operating drone system that will be offered to powerline operators to inspect the power grid accurately, frequently, and autonomously.
The aim of Drones4Safety (D4S) is to develop a system of autonomous, self-charging, and collaborative drones that can inspect a big portion of transportation infrastructures in a continuous operation.
FeatureCloud is a novel artificial intelligence (AI) platform, based on a groundbreaking new cloud infrastructure to integrate local AI globally without the need for any transfer of primary medical data – totally anonymous by default.
The obesity pandemic in westernised countries calls for novel therapeutic approaches in order to improve the life of affected individuals and to lower the societal burden. Changes in the microbiome composition poses a promising strategy for obesity treatment, however, the effects of such interventions are unfortunately far from being understood.
The MATOMIC center attacks this fundamental problem by a synergistic combination of advanced mathematical modelling techniques and wet-lab experimentation, which will culminate in a predictive model of how interventions affect the structure and composition of the microbiome.
Metabolomics of Patients with Glucocorticoid-induced Diabetes Mellitus
This interdisciplinary project is a collaboration between researchers from Nordsjællands Hospital (Dept. of Endocrinology and Nephrology), SDU (Dept. of Biochemistry and Molecular Biology, Dept. of Mathematics and Computer Science, Dept. of Public Health), the Danish Centre for Research in Type 2 Diabetes and the Medical University Graz (Dept. of Dermatology and Venerology). We study and analyze the metabolome of patients with glucocorticoid-induced diabetes mellitus (GIDM) to improve the understanding of the disease. Methods from statistical learning are applied to metabolomics data to investigate whether it is possible to distinguish patients with type 2 diabetes from those with GIDM better than currently possible.
Online Algorithms with Machine Learning Predictors
For resource optimization problems, online algorithms provide guarantees by focusing on worst-case scenarios. In contrast, machine learning focuses on the frequently occurring cases, but usually with no guarantees, which is problematic for planning and safety. This project aims at combining the best features of the two areas, using machine learning as an untrusted advisory component in an online algorithmic solution to get absolute guarantees as well as good average case behavior.
SammenOmDemens is a smartphone app for people with a mild degree of dementia, their relatives and volunteers. In its main purpose, it uses AI to detect if a person is getting lost and to activate the nearest volunteers to provide assistance.