My Research

I’m working with EEG based Brain-Computer Interfaces (BCI). The idea is to use cloud computing to make BCI systems faster and make them user-independent, meaning that it should be fast and easy for new BCI system users to start using the BCI.

I’m currently looking into the calibration part of a BCI-system and studying how that can be done more efficiently. I presented a poster at the BCI meeting. Here is a video where I summarize the poster content, and here is an abstract.

During the summer of 2021, a colleague and I built a real-time BCI system that detects workload. The idea is to use this system to investigate other interesting BCI-related things, such as the calibration for a BCI system. 

Tools

I have collected EEG data with a portable SMARTINGmobi and Muse S EEG system and used the MNE-python toolbox to process it. I use Python for everything: stimuli programs, data processing, and data analysis. For all machine learning related stuff, I use scikit-learn and TensorFlow. A colleague and I used Timeflux and Psychopy for a real-time BCI system that we built.

Funding

The WASP program funds my Ph.D. studies.

• Heskebeck, Frida. (2019). Towards autonomous antibody purification. Master’s Thesis. Department of Chemical Engineering, Lund University.
  • I was awarded a Scholarship from the Karl-Erik Sahlberg foundation for my outstanding Master’s thesis.

Master’s theses I have (co-)supervised

• Wilroth, Johanna. (2020). Domain Adaptation for Attention Steering. Master’s Thesis. Department of Automatic Control, Lund University.
  • Johanna was awarded with LTH’s jubilee scholarchip for her excellent master’s thesis!
• Andersen, Tom. (2021) Implementation of a Simple Asynchronous Pipeline Framework (SAPF) for construction of real-time BCI systems. Master’s Thesis. Department of Automatic Control, Lund University.