Loading...

Application of Error Potential in Brain-Computer Interface Systems

Sakhavi, Siavash | 2012

518 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 43486 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Shamsollahi, Mohammad Bagher
  7. Abstract:
  8. Brain computer interfaces (BCI) are systems designed to understand the brain function from activation patterns and dynamics recorded from the brain activity and use this knowledge to give disabled people the ability to communicate with their surroundings. Features are extracted from recorded signals from the brain while occupied in a mental task and classified into categories related to the task given. These classifiers are then used for the estimation of user anticipation. Usually, the tasks defined are meant to evoke or induce a potential in the pattern of the brain. Awareness of error responses is one of the cognitive functions of the brain which occurs when a response is in conflict with user desire or anticipation; observing an error from a person or system or doing a task with error evokes a potential in the brain called the Error Potential (ErrP) which can be detected in the subject's EEG pattern. This potential is an Event-Related Potential (ERP). In recent years, an area of research has been applying error potentials as a tool for error correction or learning in BCI systems. By using Error Potentials detected after a given task, the system gets a feedback from the user and can use this for the mentioned properties. Up until now, ErrPs' have been used in various BCI tasks such as motor imagery tasks, robot movement correction, the BCI-Speller and computer movement correction. In this thesis, a novel task has been defined to choose direction using error potential detection. 13 subjects (8 male and 5 female) have cooperated for EEG recording. 3 stages including discrimination analysis, feature extraction and classification has been applied to these signals. A new feature extraction method using singular value decomposition (SVD) and the analytical form of a signal has been proposed and used for results. Results given in this thesis fall into two categories: classification of error/correct trials and applying classification to the task at hand.
  9. Keywords:
  10. Singular Value Decomposition (SVD) ; Brain-Computer Interface (BCI) ; Discriminant Analysis ; Error Potential ; Signal Analytical Form

 Digital Object List

 Bookmark

No TOC