Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 39930 (05)
- University: Sharif University of Technology
- Department: Electrical Engineering
- Advisor(s): Shamsollahi, Mohammad Bagher
- Abstract:
- BCI is an interface between brain and machine, particularly computer which translates brain signals into understandable instructions for machine. BCI records signals and determines what the subject is doing or thinking. BCI in the point of view of pattern recognition is a classification problem. For this aim, different tasks are referred to different classes. The more number of classes, the higher complexity we encounter in classification so surveying of different kinds of features, feature selection and reduction methods have highly importance. In this project we want to design a 4-class classification that each class is referred to a direction of wrist movement. During the time that the subject is doing the task, MEG signal acquisition is performed. For this, two phases are considered. In former phase, our best effort is done due to find a suitable algorithm to have the best classification accuracy. The most important approach in this phase which helps us to increase the accuracy far better than the winner of BCI competition 2008, is using ULDA as a feature reduction method. Generally, it can be considered that if the numbers of channels or time samples of the data are a lot, we can have better classification. However, this is not true in real world. So in the latter phase, we search for the best subset of available channels and the best time interval. The best results achieve out of these two phases are 62% for subject 1 and 45% for subject 2 according to the accuracy criteria
- Keywords:
- Feature Extraction ; Classification ; Brain-Computer Interface (BCI) ; Magnetoencephalography (MEG)
Digital Object List
-
محتواي پايان نامه
- view
Bookmark