Loading...

Extracting activated regions of fMRI data using unsupervised learning

Davoudi, H ; Sharif University of Technology | 2009

468 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/IJCNN.2009.5178805
  3. Publisher: 2009
  4. Abstract:
  5. Clustering approaches are going to efficiently define the activated regions of the brain in fMRI studies. However, choosing appropriate clustering algorithms and defining optimal number of clusters are still key problems of these methods. In this paper, we apply an improved version of Growing Neural Gas algorithm, which automatically operates on the optimal number of clusters. The decision criterion for creating new clusters at the heart of this online clustering is taken from MB cluster validity index. Comparison with other so-called clustering methods for fMRI data analysis shows that the proposed algorithm outperforms them in both artificial and real datasets. ©2009 IEEE
  6. Keywords:
  7. Cluster validity indices ; Clustering approach ; Clustering methods ; Decision criterions ; fMRI data ; Growing neural gas ; Key problems ; Online-clustering ; Optimal number ; Real data sets ; Cluster analysis ; Neural networks ; Clustering algorithms
  8. Source: Proceedings of the International Joint Conference on Neural Networks, 14 June 2009 through 19 June 2009, Atlanta, GA ; 2009 , Pages 641-645 ; 9781424435531 (ISBN)
  9. URL: https://ieeexplore.ieee.org/document/5178805