Courses Archive

Background Today's data collection usually uses different types of sensors that store data in different formats. Therefore, a well-structured database is a useful tool for further processing of the data. Especially in context recognition tasks, annotating the merged data plays a key role in bein... Continue

Background Adolescent girls with AN undergo high levels of stress, which has been shown as risk factor in the development of eating disorders. Widely examined autonomic indices for stress reactivity are heart rate (HR) and heart rate variability (HRV, RR intervals (RRI) in electrocardiogram). Th... Continue

Background: To automate the analysis of consumed food for dietary monitoring, several approaches have been tried. Two promising ideas are a) electromyographic (EMG) monitoring of the masseter muscle, and b) acoustic measurements to capture chewing sounds. While EMG data can be used well for segment... Continue

Background Electromyography (EMG) has been extensively used in various digital health applications. In this field, miniaturization is crucial, as health data shall be recorded without influencing the daily life of the patient. To meet these requirements while avoiding signal loss, wearable designs w... Continue

Background: Novel wireless in-ear headphones can do more than playing music. They come with various types of sensors, e.g. microphones, or inertial measurement unit (IMU). In past research, earables have been used to monitor dietary activity in free living using microphones, which capture e.g. che... Continue

Background Auscultation is a standard medical practice performed by clinicians when inspecting a patient during preliminary examinations. Auscultation is usually performed by using the stethoscope to listen to the body sounds. Wearable technology can automatize listening to body sounds and make ... Continue

Background Wearable technology often requires devices to be personalized in order to achieve comfort and usability requirements for a long-term, inconspicuous monitoring of the user health. We propose to implement an algorithm to automate the customization and fitting of smart clothes under moti... Continue

Background Machine learning methods can nowadays be very helpful to automatically collect data and build large-sized datasets. However, the retrieved datasets need to be catalogued before being further processed. Classification may require expert knowledge annotation to train the algorithm, and ... Continue

Background Digital health applications (German: “Digitale Gesundheitsanwendung”, DiGA) are the basis for a rapid time-to-market of health and medical apps. This seminar starts with an international overview of digital health app regulations and an introduction to the pioneering German DiGA act. ... Continue

Course description Digital health is a branch of digital medicine that integrates and leverages multisource and multimodal data for medical knowledge extraction and decision support across a wide range of preventive, diagnostic, and therapeutic applications. The course starts by introducing the ... Continue