Project Description: Brain-Computer Interfaces have the potential to reduce suffering of patients in a complete locked-in state, i.e., patients who are unable to communicate due to full motor paralysis but who still have intact cognitive and emotional processing. Brain–computer interface (BCI) provide a promising aproach to establish communication with these fully paralyzed patients. Most current BCI systems are based on electroencephalography (EEG) in combination with machine learning algorithms.
Deep Learning methods, given enough annotated data, have proven to yield superior performance in many machine learning settings. However, in BCI research deep learning approaches have not yet shown convincing improvement over state-of-the-art BCI methods. In addition, high quality EEG systems are mostly designed for clinical practice and are cumbersome to use. However, developments in hardware are transforming EEG systems from stationary, wired systems to wearable, wireless, convenient, and comfortable lifestyle solutions. Simple and reliable BCI systems are within reach.
In this project, we are explore deep learning solutions for convenient EEG-based BCI. This research includes
- Investigating appropriate deep learning architectures for EEG-based BCI
- Investigating the optimal trade-off between performance and number of required electrodes
- Investigating influence of signal noise
This project is related to a possible internship in Philips Reserch and will involve supervision from Ulf Grossekathofer and Vlado Menkovski
Lotte, Fabien, et al. “A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update.” Journal of neural engineering 15.3 (2018): 031005.
Chaudhary, Ujwal, et al. “Brain–computer interface–based communication in the completely locked-in state.” PLoS biology 15.1 (2017): e1002593.
Mihajlovic, V., Grundlehner, B., Vullers, R., & Penders, J. (2015). Wearable, Wireless EEG Solutions in Daily Life Applications: What are we Missing?. IEEE Journal of Biomedical and Health Informatics, 1(19), 6-21.