You can write any of our staff members about open topics for practica, bachelor and master theses.
In the case of excellent performance there is also the chance to submit the thesis as an article to a computer science conference and to be co-author on a scientific publication early in your studies!
Near-infrared spectroscopy (NIRS) is used in several research areas to estimate, quantify or analyse relevant properties of materials. A spectrum shows the relation between the wavelengths and an optical quantity, like transmittance or absorbance. Given a target value, a regression model can be tuned to estimate this target by using the spectral data as input variables. These methods are also called multivariate calibration models and are analysed in the "Chemometrics" field of research.
Instead of manually fine-tuning and evaluating different regression models, your goal will be to use modern AutoML methods to search for suitable machine learning pipelines. You will evaluate different approaches and compare the found algorithms against previously proposed models for a given dataset of ~21k spectras.
Betreuer: Florian Buckermann
Photographers usually filter their photo collections for the most beautiful images and enhance them using image filters. In both (and potentially even more) steps, we can incoporate machine learning. For example, we can build neural networks that assess the aesthetics of an image. Moreover, machine learning is able to help with retouching an image (e.g. the automatic enhancement in your phone's photo app).
This topic is quite diverse and thus there are multiple topics and ideas to try. If you are interested in building and analyzing neural networks and other machine learning models to help photographers, just drop me a line.
Supervisor: Konstantin Kobs
Human intelligence is the best predictor of important life outcomes like educational and occupational success and even health and longevity. Cognitive neuroscience has recently shown that functional and structural brain data (as assessed with an MRI scanner) can predict individual intelligence scores. However, many preposing steps are involved and associated with many degrees of freedom so that the resulting “cleaned” brain signal is only a coarse approximation of the “true” underlying brain activity. This thesis aims to develop a new machine learning-based MRI artefact correction method. We will start with substituting single preprocessing steps and investigate how much of the common methodology can be replaced by more data-driven methods utilizing machine learning - without reducing prediction accuracy of phenotypic measures like intelligence, personality and age.