Dr. Michael Knierim

With the emergence of generative AI, the field of Brain-Computer Interfaces (BCI) is experiencing a surge in potential applications. For example, a recent publication in Nature Neuroscience (https://www.nature.com/articles/s41593-023-01304-9) demonstrated that large language models (LLMs) can accurately predict an individual's thoughts based on brain recordings obtained from a stationary fMRI scanner.

However, before realizing the full potential of BCI applications in real-life scenarios, a significant hurdle must be overcome: effectively dealing with the continuous presence of various recording artifacts and extracting meaningful information from wearable sensors. For instance, EEG sensors embedded in headphones, such as the ones outlined in this project (https://github.com/MKnierim/openbci-headphones), require sophisticated techniques to address these challenges. In this thesis project, you will have the unique opportunity to collect and analyze extensive datasets comprising brain, heart, and muscle signal data.

The primary objective of this project is to identify and develop methodologies that can automatically detect and remove recording artifacts from the collected data. By achieving this, we aim to enable the inductive identification of neural and physical patterns that could serve as the foundation for real-world BCI applications. Imagine a future where AI assistants, armed with access to your biosignal data, can provide personalized recommendations on how to lead a more productive and healthier lifestyle.

Your ideas and contributions in this exciting field are highly valued. Therefore, I encourage you to submit your ideas, along with your CV and transcript of records, when applying for this project.

Also, if you have any questions about the topic beforehand, please contact Michael Knierim (michael.knierim@kit.edu).

Additional Materials:

• Michael Thomas Knierim, Daniel Puhl, Gabriel Ivucic, and Tobias Röddiger. 2023. OpenBCI + 3D-Printed Headphones = Open ExG Headphones – An Open-Source Research Platform for Biopotential Earable Applications. In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems (CHI EA ’23), April 23–28, 2023, Hamburg, Germany. ACM, New York, NY, USA, 7 pages. https://doi.org/10.1145/3544549.3585875
• Knierim, M.T., Schemmer, M., Perusquía-Hernández, M. (2021). Exploring the Recognition of Facial Activities Through Around-The-Ear Electrode Arrays (cEEGrids). In: Davis, F.D., Riedl, R., vom Brocke, J., Léger, PM., Randolph, A.B., Müller-Putz, G. (eds) Information Systems and Neuroscience. NeuroIS 2021. Lecture Notes in Information Systems and Organisation, vol 52. Springer, Cham. https://doi.org/10.1007/978-3-030-88900-5_6