Valid from: Spring 2021
Decided by: Professor Thomas Johansson
Date of establishment: 2022-06-14
Division: Automatic Control
Course type: Third-cycle course
Teaching language: Swedish
Demonstrate understanding in signal processing and applications for different types of brain computer interfaces, with focus towards EEG.
Knowledge and Understanding
For a passing grade the doctoral student must Demonstrate understanding of the most commonly used BCI paradigms and how basic types of signal processing and machine learning can be applied to those paradigms, here with a focus towards EEG-based BCI systems.
Competences and Skills
For a passing grade the doctoral student must Master tools from existing Python packages such as MNE python, pyriemann, sklearn, and timeflux, to process, analyze, and/or visualize EEG-data using techniques covered in the course.
Judgement and Approach
For a passing grade the doctoral student must Demonstrate understanding of the limitations of different types of BCI paradigms and commonly used methods for signal processing of such paradigms, and be able to organize and select material for discussion seminars.
Different techniques for recording of brain activity (EEG, fMRI, invasive, non-invasive), event-related potentials (ERP), motor imagery/sensorimotor rhythms (MI/SMR), Steady-State Evoked Potentials (SSxEP), feature extraction, linear discriminant analysis (LDA), common spatial patterns (CSP), Riemannian geometry (RG), bayesian learning (BL), transfer learning (TF), BCI calibration.
Nam, C., Nijholt, A. & Lotte, F.: Brain–Computer Interfaces Handbook, Technological and Theoretical Advances.. 2018. ISBN 9781498773430.
Types of instruction: Project, self-study literature review
Examination format: Seminars given by participants.
Four seminars that span different parts of the course. Completion of a small project.
Grading scale: Failed, pass
Examiner:
Course coordinators: