Loading...

Decoding the Long Term Memory using Magnetoencephalogram

Tavakoli, Sahar | 2015

708 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 46909 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Fatemizadeh, Emad
  7. Abstract:
  8. Memory and recalling process has always been a basic question. Decoding the Long-Term_Memory is one of the first steps in answering this question. Since various experiments in the field of human long-term memory, was conducted. This research is motivated by a trial that in which, the Mgntvansfalvgram (MEG) has been recorded while recalling the color and orientation of a grading which is associated with an object, after the object has been shown. High accuracy in Decoding the mentioned color and direction, will be decoding the long-term memory. In order to enhance memory decoding, the research studies different classifiers such as sparse based classifiers and other popular one. It has also will introduce a new classification called WORM, that addition to high speed and low computational complexity, show good results in classification accuracy in testing on experimental data and synthetic one. The main idea of the method is come from compounding nearest subspace (Nearest Subspace Classifier) and sparseness idea. In this study, also, the idea of using the regression group (Group LASSO) in processing MEG, is introduced. In addition to decoding memory, connectivity between the parts of the can be Analyzed. Different parts of the brain have structural connectivity and functional connectivity, which have been proved that this functional connectivity, varies in some diseases than healthy people
  9. Keywords:
  10. Long Memeory ; Magnetoencephalography (MEG) ; Brain Connectivity ; Nearest Subspace Classifier ; Group Lasso

 Digital Object List

 Bookmark

No TOC