The chair is pursuing top-level research on foundational and applied topics of digital health. On electronic health (eHealth), members of the chair investigate data integration techniques and develop machine learning algorithms for patient data interpretation and health knowledge extraction from clinical, wearable, and ambient data. Often physiological data is being integrated with context data, acquired in free-living (out-of-lab) settings. The algorithm bandwidth stretches from time series analysis to dynamic, adaptive pattern modelling, combining data models with expert models, as well as model personalisation. In addition, embedded algorithms for sensor data analysis and probabilistic aggregation are developed and evaluated. On mobile health (mHealth) and ubiquitous health (uHealth), members of the chair are investigating novel design methods and procedures to fabricate and analyse wearable and implantable body sensor and actuator systems. We build systems using functional materials and multiprocess additive manufacturing methods. Novel sensor technologies are investigated as well as their integration in unobtrusive wearable, implantable, and home monitoring and intervention systems. The Chair of Digital Health at FAU was founded by Prof. Dr. Oliver Amft in September 2017, supported by the the Zentrum Digitalisierung.Bayern (ZD.B), the FAU Faculty of Medicine, and the FAU Erlangen-Nürnberg. The Chair of Digital Health is embedded in the Institute of Medical Informatics at the FAU Faculty of Medicine.
Current research topics include (see research project pages for more detail):
- Multimodal context recognition algorithms and methods.
- In addition, embedded algorithms for sensor data analysis and probabilistic aggregation are developed and evaluated.
- Context recognition with smartphones and smartwatches.
Coordinates of our offices and labs can be found below.
Directions to FAU can be found here. The chair has two locations in Erlangen. Our offices are located in 15 min walking distance of the Erlangen main station (or 5-6 min by bus) at Henkestr. 91. See map and address below. Our lab rooms are at the Krankenhausstr. 12.
Directions to Henkestr. 91: Out of the train station, please walk southwards along Goethestrasse until Güterhallenstrasse. Take a left and follow Güterhallenstrasse, which becomes Henkestrasse. Follow Henkestrasse. The Medical Valley Center building is on the left. From the main entrance, take a right. The offices are located at Building 7, first floor.
Directions to Krankenhausstr. 12: Out of the train station, please walk straight along ‘Universitätsstrasse’. Take a left at ‘Krankenhausstrasse’ and walk another 20m. The chair’s labs are at the ground floor and can best be reached through the entrance ‘Alte Medizin’ building part F. Please follow the signs and door plates for F00.127 and F00.128.
Address and contact information
Prof. Dr. Oliver Amft Chair of Digital Health Henkestraße 91 91052 Erlangen Tel.: +49 9131 85 23601 Room: Haus 7, OG1, 375 Assistant: Mrs. Claudia S. Uebelein Room:Haus 7, OG1, 372b Tel.: +49 9131 85 23601 e-mail: claudia.s.uebelein <AT> fau <DOT> de
ACTLab research group history
The Activity and Context recognition Technologies (ACTLab, speak: ‘act-lab’) research group was founded by Dr. Oliver Amft at the TU Eindhoven, Faculty of Electrical Engineering in 2009. In January 2014, the group moved to the University of Passau to establish the new Chair of Sensor Technology at the Faculty of Computer Science and Mathematics. In September/October 2017, the research group moved again, then to Erlangen, to become part of the new Chair of Digital Health.
Since the start in 2009, the ACTLab research group pursued fundamental and applied technical research on human behaviour and exposure analysis, and context recognition to construct intelligent ubiquitous assistants. The investigations were (and are still) motivated and reinforced by unobtrusive ambient, wearable, and mobile computing technologies that provide on-body and environment-embedded sensing and actuation functions, and processing resources. The investigations range from unobtrusive devices for on-body and ambient embedding, and algorithms for multimodal signal processing and pattern recognition, to unsupervised data mining and novel methods in artificial intelligence and machine learning. System and electronics contributions ranged from smart textiles to wearable inertial sensor nodes.
We like to thank our all our sponsors for their support.