04.11.2019 – 29.11.2019
KU Leuven, Belgium
Prof. Sabine van Huffel
For my external research stay I visited the group of Professor Sabine van Huffel at the KU Leuven in Belgium. Her group is part of the STADIUS Center for dynamical systems, signal processing and data analytics.
For four weeks I have been working on artifact removal for EEG signals. Previous research of the group focused mainly on multi-channel artifact removal, but I mainly dealt with behind-the-ear EEG consisting of only 4 electrodes.
Altogether, I worked with a lot of different algorithms that can be used for single-channel measurements, especially variations of the EMD (Empirical Mode Decomposition) and Wavelet Transformation. I learned a lot about the advantages and disadvantages of the algorithms and the assumptions that have to be fulfilled for their usage. The aim is to apply the algorithms (single channel as well as multi-channel) to the ME sensor systems in a second step and thus to enhance the output signals in a non-stationary and non-linear fashion.
At the last two days of my research stay I attended the annual IEEE EMBS Benelux chapter symposium, taking place in Leuven (Thursday) and in Brussels (Friday). The topic of the symposium was Artificial Intelligence in Healthcare.
I would like to thank Prof. van Huffel for the opportunity to visit her working group and for the insights into single- and multi-channel blind source separation techniques. Additionally, I would like to thank the German Research Foundation (DFG) for funding this research stay as part of the CRC 1261.