Principles of Brain Computer Interface

• Characterize neurophysiological EEG markers of mental activity, including sensorimotor rhythms (Mu/Beta), P300 potentials, and steady-state visual evoked potentials (SSVEP).
• Evaluate the architecture of various BCI systems and neural prostheses, comparing signal acquisition methods and their application in motor and communication restoration.
• Apply signal processing techniques to condition EEG data, utilizing temporal filters and spatial enhancement methods to mitigate ocular and myogenic artifacts.
• Engineer robust feature extraction pipelines using methods such as Common Spatial Patterns (CSP), band power estimation, and time-frequency analysis.
• Implement and validate machine learning architectures to classify mental states and motor intent from high-dimensional, non-stationary neural data.
• Integrate real-time data acquisition, online processing, and control logic to build a functional, closed-loop brain-computer interface system.
• Critically synthesize state-of-the-art research by reviewing and presenting peer-reviewed scientific articles on emerging BCI paradigms.
• Discuss the trajectory of BCI technology, focusing on ethical considerations, long-term stability, and the transition from laboratory to clinical environments.
• Utilize GenAI to architect and optimize neural classifiers, validating AI models against the specific physiological and signal-to-noise constraints of BCI data.

Brain-Computer Interface based on different types of EEGs will be covered in the form of lectures, discussions, practical and theoretical learning methods. The students will be asked to present a scientific article. A BCI design group project (group of 2) using the available BCI data or new data will be completed with a final report and a presentation.

22052/02450/02460

Lectures
Exercises
Student presentation of scientific articles
Group project work

Minimum: 10.

Please be aware that this course will only be held if the required minimum number of participants is met. You will be informed 8 days before the start of the course, whether the course will be held.