Loading...

Brain Connectivity Analysis from EEG Signals using Entropy based Measures

Saboksayr, Saman | 2018

539 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 50538 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Shamsollahi, Mohammad Bagher
  7. Abstract:
  8. Even in the simplest of activities in the brain such as resting condition, there are connections in between different regions of the brain so that the whole system functions consistently in harmony. Studies related to brain connectivity provides an opportunity to better understand how the brain works. To assess these connectivities an estimation is usually conducted based on brain signals. Among different estimation methods, quantities of information theory are in general more practical due to avoiding any assumptions toward the system model and the ability to recognize linear and non-linear connectivity. One of the main quantities related to the information theory is in fact, entropy. Therefore in this thesis, first an introduction to a variety of entropies namely, spectral, sample, permutation and transfer are given. Then a series of transfer entropy estimation methods including Binning, kernel-based, nearest neighbor-based and a linear estimator are provided in detail. Following that a development on transfer entropy estimation is presented based on hyper-ellipsoid volume together with Singh and Kozachenko-Leonenko estimators. To investigate the capability of transfer entropy estimators in recognition of effective connectivity, these methods were tested on a set of simulation data, proving that our proposed method does a better job in lower dimension data than other existing estimators. Also, a series of comparisons were made among spectral, sample, permutation and transfer entropies in recognition of functional connectivity patterns via application of these entropies on simulation data. These comparisons resulted in the fact that transfer entropy unlike the other entropies, has a considerable precision in identifying functional connectivity patterns. Finally, to further investigate the capability of transfer entropy, it was applied to a set of EEG data that was provided by Freiburg epilepsy center for a seizure prediction competition. Former studies have proven that brain connectivity in individuals with epilepsy compared to healthy ones are generally on a lower level and it further declines throughout an epileptic seizure. This has been the case for this study as well, evidently proving the validity of the attained results
  9. Keywords:
  10. Brain Connectivity ; Effective Connectivity ; Functional Connectivity ; Information Theory ; Entropy ; Electroencephalogram Signals Classification

 Digital Object List

 Bookmark

No TOC