If you want to sign up for this seminar, you need to register with the following information in the registration form

• surname, first name,
• e-mail address,
• matriculation number,

Please note that the registration period starts 07.10.2021 at 10:00 h and ends 27.10.2021 at 23:59 h. All applications before and after this registration period will not be taken into account.

Registration will be possible within the before mentioned time under the following subsite - Seminar Registration.

During the registration process you will also choose your seminar topic. Only one student per topic is permitted (first come - first serve).

The registration is binding. A deregistration is only possible by sending an e-mail with your name and matriculation number to This email address is being protected from spambots. You need JavaScript enabled to view it. until Sunday, 17.10.2021 at 23:59 h. All later cancellations of registration will be considered as having failed the seminar.

Students write a scientific report on a topic closely related to the current research of the DSS group. Potential topics, therefore, deal with digital signal processing related to medical signal processing.

Students will also present their findings in front of the other participants and the DSS group.

A tremor can occur as a symptom of various diseases and can be studied to distinguish them. Acceleration and EMG sensors can be used to analyse tremor of different body parts such as hands, arms or the head. In this seminar, an overview about possible machine learning algorithms used in the literature should be investigated. Finally, the advantages of different methods for tremor analysis should be discussed.

Magnetic sensing offers potential advantages compared to conventional recording techniques with surface electrodes for biomagnetic diagnostics. A wide variety of sensor technologies exist, and they are promising in many respects, especially in gradiometer configurations combined with digital readout schemes. In this literature study, an overall overview of magnetic sensors should be examined. Therefore advantages, disadvantages, and current limitations of the individual sensor concepts including their applied digital signal enhancement methods should be discussed.

Many sensors suffer from nonlinear effects and are thus limited in performance. The nonlinear effects can be caused by the sensor itself, as well as from the used hardware or the surrounding. In this seminar Volterra filters should be considered for performance improvement of sensors. The improvement should be determined in terms of a better system identification and noise cancellation. A comparison to other nonlinear filters is preferable.

Tracking applications often require the combination of multiple data sources to achieve a reliable estimation of an object’s attitude in 3D space. Most approaches fuse the measured data from Inertial Measurement Units (IMUs), but some might also include other sensor concepts. In this literature study multiple commonly applied Kalman filter derivatives for sensor fusion applications should be identified and compared to each other.

Computer-aided medical image analysis plays an important role in helping medical personnel diagnose and treat patients. Recently, the use of artificial neural networks has improved the state of the art for many applications, from classification (e.g., to identify cancer cells) to 3D segmentation (e.g., to segment MRI scans of the heart to diagnose certain diseases). In this seminar, you will identify and describe various algorithms and approaches based on literature reviews. The focus of your research will be 3D segmentation. For this application, you should compare different approaches in terms of their performance and complexity.

Advances in wearable sensor technology, e.g. inertial measurement units (IMUs), cause a shift from lab-based to home-based human gait analysis. Key to reliable home-based gait analysis is the accurate recognition of gait episodes, so-called walking bouts. In this seminar you will investigate which machine learning-based algorithms, preferably recurrent neural networks (RNNs) or temporal convolutional networks (TCNs) are best suited for segmentation and classification of walking bouts from acceleration signals. You will provide an overview of algorithms and to which (public) datasets they have been applied. Eventually, you will outline what methods could be applied in a cohort of neuro-degenerative disease people.