AI in healthcare and social services

Healthcare and social services present numerous opportunities where the use of AI could positively influence human quality of life and contribute to societal progress. In this area, our focus is on the methods of machine learning, in particular Deep Learning.

In the area of medical speech processing, we are developing algorithms and prototypes that support physicians in making diagnoses like Alzheimer or depression or that assist speech therapists in treating stuttering.

In the area of medial imaging, we are developing methods to support diagnosis and differentiation. For example, in lung CTs, we can differentiate regular pneumonia from COVID-19 infections using Deep Learning methods.

In the area of social services we are using natural language processing (NLP) to, for example, construct official texts more simply and comprehensibly, expand online counseling with intelligent chatbots, or to develop interactive assistants that can help with completing forms. 

Contacts:

Prof. Dr. Jens Albrecht

Prof. Dr. Tobias Bocklet

Prof. Dr. Robert Lehmann

Prof. Dr.-Ing. Jan Paulus

Prof. Dr.-Ing. Korbinian Riedhammer

AI in industrial applications

Artificial intelligence helps to analyse and optimize industrial production systems and processes qualitatively and quantitatively. Diverse data and signals are evaluated using machine learning processes. This enables automatization of different repetitive tasks, accelerates the performance of these tasks, and reduces the error rate. Predictive maintenance addresses the evaluation of machine data, in order to recognize failures or errors early and to plan exchanges, replacements, or repairs for optimal cost savings before they are urgently needed. Machine learning methods can also be used for automatic quality assurance.

Contacts:

Prof. Dr. Tobias Bocklet

Prof. Dr.-Ing. Armin Dietz

Prof. Dr.-Ing. Jan Paulus

AI in business administration applications

We follow a strictly application oriented approach. From our basic AI research, we only adopt those proposed solutions that promise a  tangible benefit in operational application fields . In addition, we are convinced that the only way to further develop the application of AI in the business context as a whole is by combining different AI sub-areas. In this respect, we consider  symbolic and sub-symbolic AI to be equally important. We do not engage in maximizing expectations of AI’s potential in a highly speculative manner, but rather are working on a realistic picture of the opportunities and risks of AI for operational application.

Contacts:

Prof. Dr. Thomas Bahlinger

Prof. Dr. Ralph Blum

Prof. Dr. Michael Maier

Prof. Dr. Roland Zimmermann

AI in robotics

Robotics encompasses all ways of looking at problems in classical  engineering sciences. With AI algorithms, machines transition to  intelligent entities. Our research in this area includes  navigation, semantic image comprehension, software engineering for safety-critical (embedded) systems, explainability of AI algorithms of highly automatic driving, and robot control architectures for autonomous decision-making.

Contacts:

Prof. Dr. Stefan May, Labor für Mobile Robotik

Prof. Dr. Jörg Roth

Prof. Dr. Ramin Tavakoli Kolagari, AS²E research group

AI in human-machine interaction

The Center for Artificial Intelligence (KIZ) features a broad range of areas related to human interaction with technology and the associated processing through machine learning techniques. Many of these areas use augmented and virtual reality as an interaction-interface and to analyse user behaviour and to draw immediate or sustained conclusions. These topics are relevant for diverse applications in the automotive branch to medical engineering to media.

Contacts:

Prof. Dr. Tobias Bocklet

Prof. Dr. Timo Götzelmann

Prof. Dr. Alexander Hahn

Prof. Dr. Patrick Harms

Prof. Dr.-Ing. Alexander von Hoffmann

Prof. Markus Kaiser

Prof. Dr.-Ing. Jan Paulus

Prof. Dr.-Ing. Korbinian Riedhammer

Prof. Tilman Zitzmann