Loading...

EEG Based Brain Computer Interface

Abbasi Sisara, Majid | 2016

573 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 49162 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Jahed, Mehran
  7. Abstract:
  8. Brain-computer interfaces (BCI) are systems which enable a user to control a device using only his or her neural activity. An important part of a brain-computer interface is an algorithm for classifying different commands that the user may want to execute. There are several neurological phenomena that can be used in a BCI. One of them is event related de-synchronization (ERD), which is a temporary decrease in power of the mu and beta brain waves. This phenomenon can be registered using electroencephalography (EEG) and occurs when a subject performs or imagines a limb movement. The goal of this thesis is to implement an algorithm that would be able to classify EEG signal for controlling an electric wheelchair. First an algorithm was provided for stimulating and SSVEP signal recorded. We used only 2 channel for recording SSVEP. PSD and Wavelet were used for EEG signal processing, and the maximum accuracy was 70.87% resulted. Two different motor imagery tasks, in which a user imagines a movement of one of the following parts of the body: left hand, right hand. Using electroencephalogram (EEG) data from the [114] we test some feature extraction techniques: band power features and time domain parameters, and two classifiers: linear discriminant analysis (LDA) and support vector machines (SVM). We test all algorithms with different parameters on the training set using cross-validation and then we verify the best four of them on the final test set. We obtained the maximum accuracy 84.60% for one group of features. This result shows that it is possible to use a fairly simple algorithm for EEG data classification and obtain good results if the parameter space for the algorithms is searched through methodically
  9. Keywords:
  10. Electroencephalography ; Brain-Computer Interface (BCI) ; Motor Imagery (MI) ; Brain Signal ; Event Related Potential (ERP) ; Steady State Visual Evoked Potential (SSVEP)

 Digital Object List

 Bookmark

No TOC