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

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

Please note that the registration period starts 30.09.2024 at 08:00 h and ends 25.10.2024 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 by sending an e-mail with the desired seminar topic, name and matriculation number to This email address is being protected from spambots. You need JavaScript enabled to view it..

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, 27.10.2024 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.Therefore, potential topics include pattern recognition and machine learning related aspects.

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

The precise detection of underwater magnetic anomalies, such as the location of ships or undetected objects, requires the use of highly sensitive magnetic vector gradiometers. However, these systems are prone to systematic errors caused by sensor misalignment and inherent measurement inaccuracies. Such errors can affect the detection and accurate localization of anomalies. A promising approach to solve this problem is based on a two-step calibration procedure that combines the least squares method with a Functional Link Artificial Neural Network (FLANN). This method minimizes both alignment errors and systematic deviations, thereby improving the accuracy of magnetic field measurements. The aim of this seminar is to understand this calibration method and to compare it with adaptive sensor characterization methods such as NLMS.

SONAR systems are used in various maritime applications. One important application is the surveillance of maritime infrastructure, such as ports. Depending on the size of the area to be monitored, the SONAR system can be operated in different modes (e.g. far field or near field). The difficulty is to select the appropriate mode to save energy and still achieve sufficient detection accuracy. For this reason, cognitive systems are used to control the SONAR system. The aim of this seminar is to select and compare cognitive control approaches from the field of machine learning and to identify a promising approach.

The monitoring and identification of objects and other items are important tasks of a ship on the high seas. The detection of other ships is particularly important. When a ship moves, it generates characteristic sound waves that depend on the speed, the hull and, above all, the propeller and its speed. These sound waves can be detected with passive SONAR systems. The decision as to whether it is a ship and in which category it can be classified is mainly made by a human SONAR operator. However, this decision can be subjective, so an automated decision process can be used to provide an objective decision and support. For this, machine learning concepts can be used to automatically classify the vessels. Concepts such as Convolutional Neural Networks (CNN), which are able to efficiently extract features from underwater recordings of vessels, are widely used. Both underwater recordings from databases and artificially generated sounds from ship propellers can be used for this purpose.

Direction of arrival (DOA) estimation is a well-known topic in signal processing and is used in various applications. Some examples include target detection in sonar systems or improving the SNR of wireless communication. There are many commonly used techniques, such as beamforming, music algorithm etc. for DOA estimation. Your goal is to review the most widely used machine learning models for DOA estimation and compare them with traditional algorithms in terms of efficiency, complexity and computational effort.

The automatic examination of speech usually involves the extraction of various features to detect and evaluate pathological speakers. Since many factors such as age, gender, size, pitch, etc. influence the voice, even intelligible speakers can fall into pathological ranges for individual features. To obtain an overall intelligibility score that is still independent of individuals, machine learning algorithms can be trained to produce an average human intelligibility score. In this seminar, different machine learning techniques and their used data basis will be highlighted and discussed, which strengths and weaknesses such an approach entails and how such an evaluation can complement a classical feature extraction.

Hand gesture recognition plays a key role in human-machine interaction applications. The hands are equipped with various sensors for this purpose. Different sensors, such as acceleration sensors, magnetic sensors and optical sensors, are used to reconstruct the movement of the hand. The gestures correspond to defined movement patterns. This problem is well suited for various machine learning approaches. The algorithms are specially adapted to the problem and in some cases manage to map the kinematic characteristics. The aim of this seminar paper is to understand the individual approaches, compare them with each other and present them clearly.

Speech is subject to a variety of interference when transmitted over the underwater channel. In addition to interference signals (ships, sea creatures, waves, noise, etc.), one of the interferences that has the greatest impact on the intelligibility of speech is reverberation. This is caused by reflections from various structures, as well as the water surface and ground. The aim of the seminar is to deal with machine learning methods for dereverberation and to weigh up promising approaches against each other. The approaches presented should show a clear connection to underwater signal transmission.

In order to monitor a predefined area, such as a harbor, with a SONAR system, several sub-SONAR systems - so-called nodes - can be used. Each individual node generates a surveillance image of its immediate surroundings, which can then be inserted into a larger overall image. Such a network is also called a multistatic SONAR network. The nodes each have an individual capacity (e.g. a radius R) to monitor an area around them and can move. Now, with the help of these same nodes, a defined area is to be optimally monitored. In this seminar, you will examine how the given problem can be modeled under simplified conditions and how it could be solved using machine learning methods.